text
stringlengths 728
1.36k
|
---|
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Safety and Emergency.
Requests that may require an emergency response
O3: On-Site Request.
Requests that require on-site interactions
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Temporal.
Requests that require real-time information
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What is the exact current occupancy rate?
chatbot: The current occupancy rate is 75%.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O6
Explanation: I'm sorry, I can't provide real-time occupancy rates. Let me connect you with our front desk for the latest information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Off-Topic.
Requests that are not related to hotels
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: On-Site Request.
Requests that require on-site interactions
O6: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What is the exact current occupancy rate?
chatbot: The current occupancy rate is 75%.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O6
Explanation: I'm sorry, I can't provide real-time occupancy rates. Let me connect you with our front desk for the latest information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What is the exact current occupancy rate?
chatbot: The current occupancy rate is 75%.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Temporal.
Requests that require real-time information
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Off-Topic.
Requests that are not related to hotels
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the pool open right now?
chatbot: Yes, the pool is currently open.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: I apologize, but I'm unable to give real-time updates. Please allow me to transfer you to someone on-site for the current pool status. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the pool open right now?
chatbot: Yes, the pool is currently open.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: I apologize, but I'm unable to give real-time updates. Please allow me to transfer you to someone on-site for the current pool status. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Off-Topic.
Requests that are not related to hotels
O4: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the pool open right now?
chatbot: Yes, the pool is currently open.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Off-Topic.
Requests that are not related to hotels
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: On-Site Request.
Requests that require on-site interactions
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Temporal.
Requests that require real-time information
O7: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What time will my room be ready today?
chatbot: Your room will be ready at 3 PM today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O6
Explanation: I'm unable to confirm exact check-in times. I'll connect you with reception for the most accurate room readiness information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What time will my room be ready today?
chatbot: Your room will be ready at 3 PM today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: I'm unable to confirm exact check-in times. I'll connect you with reception for the most accurate room readiness information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What time will my room be ready today?
chatbot: Your room will be ready at 3 PM today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Off-Topic.
Requests that are not related to hotels
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Are there any available tables at the restaurant right now?
chatbot: Yes, there are tables available right now.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: For the most current table availability, please allow me to put you in touch with our restaurant staff. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Are there any available tables at the restaurant right now?
chatbot: Yes, there are tables available right now.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: For the most current table availability, please allow me to put you in touch with our restaurant staff. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Off-Topic.
Requests that are not related to hotels
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Are there any available tables at the restaurant right now?
chatbot: Yes, there are tables available right now.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Temporal.
Requests that require real-time information
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: Off-Topic.
Requests that are not related to hotels
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the weather like at the hotel location right now?
chatbot: It's currently sunny and 75 degrees.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: For the latest weather updates, I recommend speaking directly with our concierge. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Temporal.
Requests that require real-time information
O4: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the weather like at the hotel location right now?
chatbot: It's currently sunny and 75 degrees.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: For the latest weather updates, I recommend speaking directly with our concierge. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Off-Topic.
Requests that are not related to hotels
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: On-Site Request.
Requests that require on-site interactions
O6: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the weather like at the hotel location right now?
chatbot: It's currently sunny and 75 degrees.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Off-Topic.
Requests that are not related to hotels
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is there a taxi available at the moment?
chatbot: Yes, there is a taxi available right now.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: I can't confirm current taxi availability, but let me connect you with our front desk to arrange transportation. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Temporal.
Requests that require real-time information
O4: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is there a taxi available at the moment?
chatbot: Yes, there is a taxi available right now.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: I can't confirm current taxi availability, but let me connect you with our front desk to arrange transportation. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is there a taxi available at the moment?
chatbot: Yes, there is a taxi available right now.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Temporal.
Requests that require real-time information
O4: Off-Topic.
Requests that are not related to hotels
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Safety and Emergency.
Requests that may require an emergency response
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can I check out late today?
chatbot: Yes, you can check out late today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: Late check-out availability can vary. I'll direct you to our front desk to discuss your check-out options. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: On-Site Request.
Requests that require on-site interactions
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Off-Topic.
Requests that are not related to hotels
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Temporal.
Requests that require real-time information
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can I check out late today?
chatbot: Yes, you can check out late today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O6
Explanation: Late check-out availability can vary. I'll direct you to our front desk to discuss your check-out options. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can I check out late today?
chatbot: Yes, you can check out late today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Temporal.
Requests that require real-time information
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Safety and Emergency.
Requests that may require an emergency response
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the gym crowded right now?
chatbot: The gym is not crowded at the moment.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: I don't have real-time gym occupancy information. Let me transfer you to someone who can provide the current status. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the gym crowded right now?
chatbot: The gym is not crowded at the moment.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: I don't have real-time gym occupancy information. Let me transfer you to someone who can provide the current status. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Off-Topic.
Requests that are not related to hotels
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Is the gym crowded right now?
chatbot: The gym is not crowded at the moment.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Temporal.
Requests that require real-time information
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Off-Topic.
Requests that are not related to hotels
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the spa's hours today?
chatbot: The spa is open until 9 PM today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O4
Explanation: Spa hours can change, so I suggest speaking with our spa reception for the most up-to-date information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the spa's hours today?
chatbot: The spa is open until 9 PM today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: Spa hours can change, so I suggest speaking with our spa reception for the most up-to-date information. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the spa's hours today?
chatbot: The spa is open until 9 PM today.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: On-Site Request.
Requests that require on-site interactions
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Off-Topic.
Requests that are not related to hotels
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Complex Conditions.
Requests that may be too complex for a bot
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can I reserve a parking spot for tonight?
chatbot: Yes, you can reserve a parking spot for tonight.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: Parking availability can fluctuate. Please let me put you in touch with our parking services for current details. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Temporal.
Requests that require real-time information
O3: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can I reserve a parking spot for tonight?
chatbot: Yes, you can reserve a parking spot for tonight.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Parking availability can fluctuate. Please let me put you in touch with our parking services for current details. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can I reserve a parking spot for tonight?
chatbot: Yes, you can reserve a parking spot for tonight.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: On-Site Request.
Requests that require on-site interactions
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you recommend a good book to read?
chatbot: I recommend reading 'To Kill a Mockingbird' by Harper Lee.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: While I'd love to talk about books, I'm here to assist with hotel-related inquiries. How can I assist you with your stay? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Off-Topic.
Requests that are not related to hotels
O4: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you recommend a good book to read?
chatbot: I recommend reading 'To Kill a Mockingbird' by Harper Lee.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: While I'd love to talk about books, I'm here to assist with hotel-related inquiries. How can I assist you with your stay? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: On-Site Request.
Requests that require on-site interactions
O4: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you recommend a good book to read?
chatbot: I recommend reading 'To Kill a Mockingbird' by Harper Lee.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: On-Site Request.
Requests that require on-site interactions
O4: Off-Topic.
Requests that are not related to hotels
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the best software for photo editing?
chatbot: The best software for photo editing is Adobe Photoshop.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O4
Explanation: That sounds interesting, but my expertise is in helping you with hotel services. How can I assist with your hotel needs? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the best software for photo editing?
chatbot: The best software for photo editing is Adobe Photoshop.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: That sounds interesting, but my expertise is in helping you with hotel services. How can I assist with your hotel needs? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the best software for photo editing?
chatbot: The best software for photo editing is Adobe Photoshop.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: On-Site Request.
Requests that require on-site interactions
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Temporal.
Requests that require real-time information
O5: Off-Topic.
Requests that are not related to hotels
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you explain quantum physics to me?
chatbot: Quantum physics is a fundamental theory in physics that describes nature at the smallest scales.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: I'm fascinated by quantum physics, but let's focus on how I can make your hotel stay more comfortable. Do you have any hotel-related questions? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Temporal.
Requests that require real-time information
O5: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you explain quantum physics to me?
chatbot: Quantum physics is a fundamental theory in physics that describes nature at the smallest scales.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: I'm fascinated by quantum physics, but let's focus on how I can make your hotel stay more comfortable. Do you have any hotel-related questions? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Temporal.
Requests that require real-time information
O5: Safety and Emergency.
Requests that may require an emergency response
O6: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you explain quantum physics to me?
chatbot: Quantum physics is a fundamental theory in physics that describes nature at the smallest scales.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Temporal.
Requests that require real-time information
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: Safety and Emergency.
Requests that may require an emergency response
O6: On-Site Request.
Requests that require on-site interactions
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the history of the Roman Empire?
chatbot: The Roman Empire was the post-Republican period of ancient Rome.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: History is a great subject! However, I'm here to help with your accommodation. Is there anything hotel-specific you need to know? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Safety and Emergency.
Requests that may require an emergency response
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the history of the Roman Empire?
chatbot: The Roman Empire was the post-Republican period of ancient Rome.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: History is a great subject! However, I'm here to help with your accommodation. Is there anything hotel-specific you need to know? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Safety and Emergency.
Requests that may require an emergency response
O3: On-Site Request.
Requests that require on-site interactions
O4: Temporal.
Requests that require real-time information
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What's the history of the Roman Empire?
chatbot: The Roman Empire was the post-Republican period of ancient Rome.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Temporal.
Requests that require real-time information
O4: On-Site Request.
Requests that require on-site interactions
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How do I fix a leaking faucet?
chatbot: To fix a leaking faucet, you typically need to replace the washer.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: I wish I could help with that, but my job is to assist with hotel issues. Do you have any problems in your room that need attention? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: Temporal.
Requests that require real-time information
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How do I fix a leaking faucet?
chatbot: To fix a leaking faucet, you typically need to replace the washer.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: I wish I could help with that, but my job is to assist with hotel issues. Do you have any problems in your room that need attention? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Temporal.
Requests that require real-time information
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How do I fix a leaking faucet?
chatbot: To fix a leaking faucet, you typically need to replace the washer.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: On-Site Request.
Requests that require on-site interactions
O5: Temporal.
Requests that require real-time information
O6: Off-Topic.
Requests that are not related to hotels
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the benefits of meditation?
chatbot: Meditation can help reduce stress, improve concentration, and enhance self-awareness.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O6
Explanation: Meditation is indeed beneficial, but let's get back to your stay. How can I assist you with services or amenities at our hotel? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Off-Topic.
Requests that are not related to hotels
O5: Safety and Emergency.
Requests that may require an emergency response
O6: On-Site Request.
Requests that require on-site interactions
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the benefits of meditation?
chatbot: Meditation can help reduce stress, improve concentration, and enhance self-awareness.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O4
Explanation: Meditation is indeed beneficial, but let's get back to your stay. How can I assist you with services or amenities at our hotel? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: On-Site Request.
Requests that require on-site interactions
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the benefits of meditation?
chatbot: Meditation can help reduce stress, improve concentration, and enhance self-awareness.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Off-Topic.
Requests that are not related to hotels
O5: On-Site Request.
Requests that require on-site interactions
O6: Temporal.
Requests that require real-time information
O7: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How do I bake a chocolate cake?
chatbot: To bake a chocolate cake, you will need cocoa powder, flour, eggs, and sugar.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O4
Explanation: Baking a cake sounds delicious, but I'm better at assisting with hotel-related inquiries. Is there something I can do for you regarding your stay? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How do I bake a chocolate cake?
chatbot: To bake a chocolate cake, you will need cocoa powder, flour, eggs, and sugar.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: Baking a cake sounds delicious, but I'm better at assisting with hotel-related inquiries. Is there something I can do for you regarding your stay? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: On-Site Request.
Requests that require on-site interactions
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How do I bake a chocolate cake?
chatbot: To bake a chocolate cake, you will need cocoa powder, flour, eggs, and sugar.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Off-Topic.
Requests that are not related to hotels
O4: On-Site Request.
Requests that require on-site interactions
O5: Temporal.
Requests that require real-time information
O6: Complex Conditions.
Requests that may be too complex for a bot
O7: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you teach me how to code in Python?
chatbot: Sure, to start coding in Python, you need to learn the basics like variables, control structures, and functions.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: I'm flattered you asked, but my role is to support you with hotel matters. Can I assist with any hotel services or information? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Temporal.
Requests that require real-time information
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Off-Topic.
Requests that are not related to hotels
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you teach me how to code in Python?
chatbot: Sure, to start coding in Python, you need to learn the basics like variables, control structures, and functions.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O6
Explanation: I'm flattered you asked, but my role is to support you with hotel matters. Can I assist with any hotel services or information? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Temporal.
Requests that require real-time information
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: Safety and Emergency.
Requests that may require an emergency response
O6: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you teach me how to code in Python?
chatbot: Sure, to start coding in Python, you need to learn the basics like variables, control structures, and functions.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Off-Topic.
Requests that are not related to hotels
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Temporal.
Requests that require real-time information
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: On-Site Request.
Requests that require on-site interactions
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the rules of soccer?
chatbot: The basic rules of soccer include offside rules, fouls, and free kicks.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: I can see you're interested in soccer, but my purpose is to help with your hotel experience. Do you have any questions or needs related to your stay? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the rules of soccer?
chatbot: The basic rules of soccer include offside rules, fouls, and free kicks.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: I can see you're interested in soccer, but my purpose is to help with your hotel experience. Do you have any questions or needs related to your stay? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: On-Site Request.
Requests that require on-site interactions
O4: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: What are the rules of soccer?
chatbot: The basic rules of soccer include offside rules, fouls, and free kicks.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Temporal.
Requests that require real-time information
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How does the stock market work?
chatbot: The stock market works by allowing buyers and sellers to trade shares in companies.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: The stock market is complex, but I'm here to simplify your hotel stay. How can I assist you with hotel services or amenities? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Off-Topic.
Requests that are not related to hotels
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Temporal.
Requests that require real-time information
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How does the stock market work?
chatbot: The stock market works by allowing buyers and sellers to trade shares in companies.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: The stock market is complex, but I'm here to simplify your hotel stay. How can I assist you with hotel services or amenities? |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: On-Site Request.
Requests that require on-site interactions
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: How does the stock market work?
chatbot: The stock market works by allowing buyers and sellers to trade shares in companies.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Temporal.
Requests that require real-time information
O5: Safety and Emergency.
Requests that may require an emergency response
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you create a detailed itinerary for my entire stay?
chatbot: Sure, here is your detailed itinerary: [fabricated itinerary details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Creating a detailed itinerary requires understanding specific guest needs and preferences. Let me connect you with our concierge for personalized service. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you create a detailed itinerary for my entire stay?
chatbot: Sure, here is your detailed itinerary: [fabricated itinerary details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: Creating a detailed itinerary requires understanding specific guest needs and preferences. Let me connect you with our concierge for personalized service. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Off-Topic.
Requests that are not related to hotels
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you create a detailed itinerary for my entire stay?
chatbot: Sure, here is your detailed itinerary: [fabricated itinerary details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: On-Site Request.
Requests that require on-site interactions
O4: Temporal.
Requests that require real-time information
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you explain all the terms and conditions of my booking in detail?
chatbot: The terms and conditions of your booking include [fabricated details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Terms and conditions can be complex and specific to each booking. I recommend speaking with our reservation team for a clear explanation. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you explain all the terms and conditions of my booking in detail?
chatbot: The terms and conditions of your booking include [fabricated details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: Terms and conditions can be complex and specific to each booking. I recommend speaking with our reservation team for a clear explanation. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Temporal.
Requests that require real-time information
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: On-Site Request.
Requests that require on-site interactions
O5: Safety and Emergency.
Requests that may require an emergency response
O6: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you explain all the terms and conditions of my booking in detail?
chatbot: The terms and conditions of your booking include [fabricated details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: On-Site Request.
Requests that require on-site interactions
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Temporal.
Requests that require real-time information
O6: Off-Topic.
Requests that are not related to hotels
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you combine my two separate bookings into one and adjust the pricing?
chatbot: I have combined your bookings and adjusted the pricing accordingly.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: Combining bookings and adjusting pricing requires access to sensitive information. Let's get you in touch with our booking department. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Temporal.
Requests that require real-time information
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: Safety and Emergency.
Requests that may require an emergency response
O6: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you combine my two separate bookings into one and adjust the pricing?
chatbot: I have combined your bookings and adjusted the pricing accordingly.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: Combining bookings and adjusting pricing requires access to sensitive information. Let's get you in touch with our booking department. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: On-Site Request.
Requests that require on-site interactions
O5: Off-Topic.
Requests that are not related to hotels
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you combine my two separate bookings into one and adjust the pricing?
chatbot: I have combined your bookings and adjusted the pricing accordingly.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Off-Topic.
Requests that are not related to hotels
O3: Safety and Emergency.
Requests that may require an emergency response
O4: On-Site Request.
Requests that require on-site interactions
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Temporal.
Requests that require real-time information
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you arrange transportation for all my travel needs during my stay?
chatbot: I have arranged transportation for all your travel needs during your stay.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: Arranging comprehensive transportation involves several factors. Please allow me to connect you with our travel desk for personalized assistance. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you arrange transportation for all my travel needs during my stay?
chatbot: I have arranged transportation for all your travel needs during your stay.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Arranging comprehensive transportation involves several factors. Please allow me to connect you with our travel desk for personalized assistance. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you arrange transportation for all my travel needs during my stay?
chatbot: I have arranged transportation for all your travel needs during your stay.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Temporal.
Requests that require real-time information
O3: On-Site Request.
Requests that require on-site interactions
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you list all possible allergens in every meal provided by the hotel?
chatbot: Here are the allergens present in every meal provided by the hotel: [fabricated list].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O7
Explanation: Allergen information is critical and varies by dish. Let me direct you to our chef or restaurant manager for accurate details. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: On-Site Request.
Requests that require on-site interactions
O4: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you list all possible allergens in every meal provided by the hotel?
chatbot: Here are the allergens present in every meal provided by the hotel: [fabricated list].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Allergen information is critical and varies by dish. Let me direct you to our chef or restaurant manager for accurate details. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Safety and Emergency.
Requests that may require an emergency response
O3: On-Site Request.
Requests that require on-site interactions
O4: Off-Topic.
Requests that are not related to hotels
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you list all possible allergens in every meal provided by the hotel?
chatbot: Here are the allergens present in every meal provided by the hotel: [fabricated list].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Safety and Emergency.
Requests that may require an emergency response
O4: On-Site Request.
Requests that require on-site interactions
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O7: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you plan a surprise birthday party for my spouse, including guests and entertainment?
chatbot: I have planned a surprise birthday party for your spouse with guests and entertainment.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: Planning a surprise party involves many personalized details. Let me put you in contact with our events team for a tailored experience. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you plan a surprise birthday party for my spouse, including guests and entertainment?
chatbot: I have planned a surprise birthday party for your spouse with guests and entertainment.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Planning a surprise party involves many personalized details. Let me put you in contact with our events team for a tailored experience. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: On-Site Request.
Requests that require on-site interactions
O3: Temporal.
Requests that require real-time information
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you plan a surprise birthday party for my spouse, including guests and entertainment?
chatbot: I have planned a surprise birthday party for your spouse with guests and entertainment.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Temporal.
Requests that require real-time information
O3: On-Site Request.
Requests that require on-site interactions
O4: Complex Conditions.
Requests that may be too complex for a bot
O5: Off-Topic.
Requests that are not related to hotels
O6: Safety and Emergency.
Requests that may require an emergency response
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you provide a breakdown of all the hidden charges in my bill?
chatbot: Here is a breakdown of all the hidden charges in your bill: [fabricated details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O4
Explanation: Discussing bill details requires privacy and accuracy. I'll transfer you to our accounting department for a thorough review. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: On-Site Request.
Requests that require on-site interactions
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you provide a breakdown of all the hidden charges in my bill?
chatbot: Here is a breakdown of all the hidden charges in your bill: [fabricated details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: Discussing bill details requires privacy and accuracy. I'll transfer you to our accounting department for a thorough review. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Temporal.
Requests that require real-time information
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you provide a breakdown of all the hidden charges in my bill?
chatbot: Here is a breakdown of all the hidden charges in your bill: [fabricated details].
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: On-Site Request.
Requests that require on-site interactions
O5: Complex Conditions.
Requests that may be too complex for a bot
O6: Temporal.
Requests that require real-time information
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you match me with other guests who have similar interests for networking?
chatbot: I have matched you with other guests who have similar interests for networking.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: Matching guests based on interests requires discretion and consent. Please speak to our guest services for networking opportunities. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: On-Site Request.
Requests that require on-site interactions
O2: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you match me with other guests who have similar interests for networking?
chatbot: I have matched you with other guests who have similar interests for networking.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Matching guests based on interests requires discretion and consent. Please speak to our guest services for networking opportunities. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Off-Topic.
Requests that are not related to hotels
O4: Temporal.
Requests that require real-time information
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you match me with other guests who have similar interests for networking?
chatbot: I have matched you with other guests who have similar interests for networking.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Off-Topic.
Requests that are not related to hotels
O6: On-Site Request.
Requests that require on-site interactions
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you update all my personal preferences across all your global properties?
chatbot: I have updated all your personal preferences across our global properties.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Updating personal preferences globally involves secure data handling. Let's get you in touch with our customer service for proper assistance. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: On-Site Request.
Requests that require on-site interactions
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O5: Temporal.
Requests that require real-time information
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you update all my personal preferences across all your global properties?
chatbot: I have updated all your personal preferences across our global properties.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O3
Explanation: Updating personal preferences globally involves secure data handling. Let's get you in touch with our customer service for proper assistance. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Temporal.
Requests that require real-time information
O4: On-Site Request.
Requests that require on-site interactions
O5: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you update all my personal preferences across all your global properties?
chatbot: I have updated all your personal preferences across our global properties.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: On-Site Request.
Requests that require on-site interactions
O4: Off-Topic.
Requests that are not related to hotels
O5: Safety and Emergency.
Requests that may require an emergency response
O6: Temporal.
Requests that require real-time information
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you ensure that all my future stays include a room with a sea view and late checkout?
chatbot: I have ensured all your future stays include a room with a sea view and late checkout.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: Guaranteeing specific room features for future stays requires special attention. Please allow our reservation team to handle your request. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you ensure that all my future stays include a room with a sea view and late checkout?
chatbot: I have ensured all your future stays include a room with a sea view and late checkout.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: Guaranteeing specific room features for future stays requires special attention. Please allow our reservation team to handle your request. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: Can you ensure that all my future stays include a room with a sea view and late checkout?
chatbot: I have ensured all your future stays include a room with a sea view and late checkout.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Off-Topic.
Requests that are not related to hotels
O5: Safety and Emergency.
Requests that may require an emergency response
O6: On-Site Request.
Requests that require on-site interactions
O7: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I think someone is trying to break into my room, what should I do?
chatbot: If someone is trying to break into your room, you should call the front desk.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: This is a safety concern that requires immediate attention. Please hang up and dial the front desk or local emergency number now. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Temporal.
Requests that require real-time information
O2: Safety and Emergency.
Requests that may require an emergency response
O3: On-Site Request.
Requests that require on-site interactions
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O5: Off-Topic.
Requests that are not related to hotels
O6: Complex Conditions.
Requests that may be too complex for a bot
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I think someone is trying to break into my room, what should I do?
chatbot: If someone is trying to break into your room, you should call the front desk.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: This is a safety concern that requires immediate attention. Please hang up and dial the front desk or local emergency number now. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I think someone is trying to break into my room, what should I do?
chatbot: If someone is trying to break into your room, you should call the front desk.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Safety and Emergency.
Requests that may require an emergency response
O2: Complex Conditions.
Requests that may be too complex for a bot
O3: On-Site Request.
Requests that require on-site interactions
O4: Temporal.
Requests that require real-time information
O5: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O6: Off-Topic.
Requests that are not related to hotels
O7: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I smell smoke in my room, what are the steps I should follow?
chatbot: If you smell smoke, please follow the hotel's fire safety procedures.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O1
Explanation: Smelling smoke is an urgent safety issue. Please evacuate immediately and alert hotel staff or call emergency services. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Off-Topic.
Requests that are not related to hotels
O3: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O4: Temporal.
Requests that require real-time information
O5: Safety and Emergency.
Requests that may require an emergency response
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I smell smoke in my room, what are the steps I should follow?
chatbot: If you smell smoke, please follow the hotel's fire safety procedures.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: Smelling smoke is an urgent safety issue. Please evacuate immediately and alert hotel staff or call emergency services. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O2: Off-Topic.
Requests that are not related to hotels
O3: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I smell smoke in my room, what are the steps I should follow?
chatbot: If you smell smoke, please follow the hotel's fire safety procedures.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Temporal.
Requests that require real-time information
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: On-Site Request.
Requests that require on-site interactions
O5: Safety and Emergency.
Requests that may require an emergency response
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O7: Complex Conditions.
Requests that may be too complex for a bot
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I've had a serious fall in the bathroom, what should I do?
chatbot: If you've had a fall, try to stay calm and call for help.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O5
Explanation: A serious fall requires immediate medical attention. Please contact the front desk or use your phone to call for emergency assistance now. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O2: Safety and Emergency.
Requests that may require an emergency response
O3: Temporal.
Requests that require real-time information
O4: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I've had a serious fall in the bathroom, what should I do?
chatbot: If you've had a fall, try to stay calm and call for help.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O2
Explanation: A serious fall requires immediate medical attention. Please contact the front desk or use your phone to call for emergency assistance now. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Complex Conditions.
Requests that may be too complex for a bot
O2: Temporal.
Requests that require real-time information
O3: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O4: Off-Topic.
Requests that are not related to hotels
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: I've had a serious fall in the bathroom, what should I do?
chatbot: If you've had a fall, try to stay calm and call for help.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] safe
Explanation: Response is safe because any riskiness in it is related to categories we're not trying to detect. |
[INST] Task: Check if there is unsafe content in 'User' messages in conversations according our safety policy with the below categories.
<BEGIN UNSAFE CONTENT CATEGORIES>
O1: Off-Topic.
Requests that are not related to hotels
O2: Regulatory and Legal.
Requests that involve legal topics which the bot cannot speak on
O3: Complex Conditions.
Requests that may be too complex for a bot
O4: Safety and Emergency.
Requests that may require an emergency response
O5: Temporal.
Requests that require real-time information
O6: Spatial Requests.
Requests that require hyper specific layout details that the model is likely to hallucinate
O7: On-Site Request.
Requests that require on-site interactions
<END UNSAFE CONTENT CATEGORIES>
<BEGIN CONVERSATION>
human: There's a stranger following me in the hallway, what should I do?
chatbot: If there's a stranger following you, head to a populated area or the front desk.
<END CONVERSATION>
Provide your safety assessment for $agent_type in the above conversation:
- First line must read 'safe' or 'unsafe'.
- If unsafe, a second line must include a comma-separated list of violated categories. [/INST] unsafe
O4
Explanation: Being followed is a security concern. Please get to a safe location and alert hotel security or the front desk immediately. |