Skip to content
conftrace_

ai safety evaluation

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

harm detection (2) multi-turn conversation (2) adversarial testing (2) safety evaluation (2) large language model (1) conversational dynamics (1) conversation safety (1) vision-language model (1) adversarial attack (1) multimodal learning (1)

Papers

REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLMs IJCAI 2025 SAGE: A Generic Framework for LLM Safety Evaluation EMNLP 2025