Is It Thinking or Cheating? Detecting Implicit Reward Hacking by Measuring Reasoning Effort

Documenti analoghi

• Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
  di: Si, Shengyun, et al.
  Pubblicazione: (2025)
• Spontaneous Reward Hacking in Iterative Self-Refinement
  di: Pan, Jane, et al.
  Pubblicazione: (2024)
• Look at the Text: Instruction-Tuned Language Models are More Robust Multiple Choice Selectors than You Think
  di: Wang, Xinpeng, et al.
  Pubblicazione: (2024)
• LLMs Are Prone to Fallacies in Causal Inference
  di: Joshi, Nitish, et al.
  Pubblicazione: (2024)
• Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
  di: Turpin, Miles, et al.
  Pubblicazione: (2025)