Teaching Models to Balance Resisting and Accepting Persuasion
Paper
•
2410.14596
•
Published
•
3
•
2
Elias Stengel-Eskin
esteng
·
AI & ML interests
NLP, computational semantics, grounding
Recent Activity
authored
a paper
2 days ago
UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
authored
a paper
22 days ago
Learning to Generate Unit Tests for Automated Debugging
upvoted
a
paper
4 months ago
Teaching Models to Balance Resisting and Accepting Persuasion
Organizations
esteng's activity
commented
a
paper
4 months ago