Problem Solving with Language Models
•
1
Haritz Puerto
haritzpuerto
AI & ML interests
Reasoning in LLMs, Question Answering
Recent Activity
published
an
article
about 18 hours ago
Problem Solving with Language Models
updated
a dataset
about 20 hours ago
haritzpuerto/scaling_mia_results
published
a dataset
3 days ago
haritzpuerto/scaling_mia_results
Articles
Organizations
Posts
2
Post
589
I just got my first ChatGPT review on ARR! 😅 Any advice on how to prove it's AI-generated? Thanks!
Post
1449
I'm excited to announce that my internship paper at Parameter Lab was accepted to Findings of #NAACL2025 🎉
TLDR: Stating an LLM was trained on a sentence might not be possible 😥 , but it is possible for large enough amounts of tokens, such as long documents or multiple documents! 🤯
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models (2411.00154)
🔗 https://github.com/parameterlab/mia-scaling
TLDR: Stating an LLM was trained on a sentence might not be possible 😥 , but it is possible for large enough amounts of tokens, such as long documents or multiple documents! 🤯
Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models (2411.00154)
🔗 https://github.com/parameterlab/mia-scaling
Collections
2
Models from the paper "Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models"
-
Fine-Tuning with Divergent Chains of Thought Boosts Reasoning Through Self-Correction in Language Models
Paper • 2407.03181 • Published • 1 -
haritzpuerto/LLaMA2-7B-dcot
Text Generation • Updated • 114 • 2 -
haritzpuerto/LLaMA2-13B-dcot
Text Generation • Updated • 6 -
haritzpuerto/LLaMA2-70B-dcot
Text Generation • Updated • 2
Samples used for the NAACL 2025 Findings paper: "Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models."
models
26
haritzpuerto/phi-1.5-dcot
Text Generation
•
Updated
•
3
haritzpuerto/phi-2-dcot
Text Generation
•
Updated
•
4
•
1
haritzpuerto/LLaMA2-70B-dcot
Text Generation
•
Updated
•
2
haritzpuerto/LLaMA2-13B-dcot
Text Generation
•
Updated
•
6
haritzpuerto/LLaMA2-7B-dcot
Text Generation
•
Updated
•
114
•
2
haritzpuerto/MetaQA
Question Answering
•
Updated
•
119
•
1
haritzpuerto/test_squad_adapter
Updated
haritzpuerto/bert-base-uncased-pf-squad
Question Answering
•
Updated
•
4
haritzpuerto/tweac_8_test
Text Classification
•
Updated
•
5
haritzpuerto/bert-base-uncased-pf-squad_v2-onnx-3
Question Answering
•
Updated
datasets
28
haritzpuerto/scaling_mia_results
Updated
•
19
haritzpuerto/RAGDOLL
Viewer
•
Updated
•
400
•
41
haritzpuerto/scaling_mia
Preview
•
Updated
•
44
haritzpuerto/the_pile_00_Gutenberg_PG-19
Viewer
•
Updated
•
2.34k
•
44
haritzpuerto/the_pile_00_PubMed_Central
Viewer
•
Updated
•
202k
•
49
•
1
haritzpuerto/the_pile_00_Ubuntu_IRC
Viewer
•
Updated
•
666
•
41
haritzpuerto/the_pile_00_USPTO_Backgrounds
Viewer
•
Updated
•
393k
•
50
haritzpuerto/the_pile_00_NIH_ExPorter
Viewer
•
Updated
•
63.3k
•
39
haritzpuerto/the_pile_00_PubMed_Abstracts
Viewer
•
Updated
•
1.04M
•
188
•
2
haritzpuerto/the_pile_00_DM_Mathematics
Viewer
•
Updated
•
67.4k
•
46