Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation

Documenti analoghi

• DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
  di: Zhang, Junbo, et al.
  Pubblicazione: (2026)
• Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models
  di: Shen, Guobin, et al.
  Pubblicazione: (2024)
• Representation Bending for Large Language Model Safety
  di: Yousefpour, Ashkan, et al.
  Pubblicazione: (2025)
• ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models
  di: Zhao, Yunhan, et al.
  Pubblicazione: (2026)
• S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
  di: Yuan, Xiaohan, et al.
  Pubblicazione: (2024)