Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection

Documenti analoghi

• Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
  di: Liu, Junhao, et al.
  Pubblicazione: (2025)
• Proxy-RLHF: Decoupling Generation and Alignment in Large Language Model with Proxy
  di: Zhu, Yu, et al.
  Pubblicazione: (2024)
• LongAlign: A Recipe for Long Context Alignment of Large Language Models
  di: Bai, Yushi, et al.
  Pubblicazione: (2024)
• Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
  di: Zhang, Zhenyu, et al.
  Pubblicazione: (2024)
• LongReward: Improving Long-context Large Language Models with AI Feedback
  di: Zhang, Jiajie, et al.
  Pubblicazione: (2024)