Expected Harm: Rethinking Safety Evaluation of (Mis)Aligned LLMs
Paper
• 2602.01600 • Published
• 21
theblackcat102
theblackcat102
AI & ML interests
None yet
Recent Activity
updated
a dataset 7 days ago
theblackcat102/gqa-testdev-balanced published
a dataset 7 days ago
theblackcat102/gqa-testdev-balanced updated
a dataset 21 days ago
theblackcat102/reasoning-gym-merged-with-samples Organizations
upvoted a paper about 1 month ago
upvoted a paper 3 months ago
upvoted 3 papers about 1 year ago
Answer, Refuse, or Guess? Investigating Risk-Aware Decision Making in Language Models
Paper
• 2503.01332 • Published
• 1
None of the Above, Less of the Right: Parallel Patterns between Humans and LLMs on Multi-Choice Questions Answering
Paper
• 2503.01550 • Published
• 1
Clear Minds Think Alike: What Makes LLM Fine-tuning Robust? A Study of Token Perplexity
Paper
• 2501.14315 • Published
• 2