類似資料

• Breaking the Mirror: Activation-Based Mitigation of Self-Preference in LLM Evaluators
  著者:: Roytburg, Dani, 等
  出版事項: (2025)
• Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
  著者:: Roytburg, Dani, 等
  出版事項: (2026)
• BatchTopK Sparse Autoencoders
  著者:: Bussmann, Bart, 等
  出版事項: (2024)
• Intrinsic Self-Correction in LLMs: Towards Explainable Prompting via Mechanistic Interpretability
  著者:: Lee, Yu-Ting, 等
  出版事項: (2025)
• Guided Self-Evolving LLMs with Minimal Human Supervision
  著者:: Yu, Wenhao, 等
  出版事項: (2025)