Self-Correcting RAG: Enhancing Faithfulness via MMKP Context Selection and NLI-Guided MCTS

Documenti analoghi

• RCBSF: A Multi-Agent Framework for Automated Contract Revision via Stackelberg Game
  di: Xu, Shijia, et al.
  Pubblicazione: (2026)
• Correctness is not Faithfulness in RAG Attributions
  di: Wallat, Jonas, et al.
  Pubblicazione: (2024)
• Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
  di: Wu, Di, et al.
  Pubblicazione: (2025)
• ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
  di: Zhang, Dan, et al.
  Pubblicazione: (2024)
• Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
  di: Quan, Xin, et al.
  Pubblicazione: (2025)