conftrace_

harmfulness evaluation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

jailbreak benchmark (1) large language model (1) jailbreak prompt (1) attack success rate (1) human annotation (1) content safety (1) safety fine-tuning (1) model comparison (1) harmful content (1) model safety (1)

Papers

Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet ACL 2025 A StrongREJECT for Empty Jailbreaks NeurIPS 2024