conftrace_

harm detection

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (3) safety evaluation (3) ai safety evaluation (2) multi-turn conversation (2) adversarial testing (2) safety alignment (2) ai safety (2) societal impact (1) activation steering (1) ethical ai (1)

Papers

Differentiated Directional Intervention: A Framework for Evading LLM Safety Alignment AAAI 2026 A Comparative Analysis of Ethical and Safety Gaps in LLMs using Relative Danger Coefficient NAACL 2025 Beyond Reactive Safety: Risk-Aware LLM Alignment via Long-Horizon Simulation ACL 2025 REVEAL: Multi-turn Evaluation of Image-Input Harms for Vision LLMs IJCAI 2025 SAGE: A Generic Framework for LLM Safety Evaluation EMNLP 2025 MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024 NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification COLING 2024 COBRA Frames: Contextual Reasoning about Effects and Harms of Offensive Statements ACL 2023