Learn to Refuse: Making Large Language Models More Controllable and Reliable through Knowledge Scope Limitation and Refusal Mechanism

Documenti analoghi

• Linearly Decoding Refused Knowledge in Aligned Language Models
  di: Shrivastava, Aryan, et al.
  Pubblicazione: (2025)
• Measuring and Eliminating Refusals in Military Large Language Models
  di: FitzGerald, Jack, et al.
  Pubblicazione: (2026)
• OR-Bench: An Over-Refusal Benchmark for Large Language Models
  di: Cui, Justin, et al.
  Pubblicazione: (2024)
• RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
  di: Muhamed, Aashiq, et al.
  Pubblicazione: (2025)
• Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
  di: Pan, Wenbo, et al.
  Pubblicazione: (2025)