Explanation, Debate, Align: A Weak-to-Strong Framework for Language Model Generalization

Documenti analoghi

• H-Net++: Hierarchical Dynamic Chunking for Tokenizer-Free Language Modelling in Morphologically-Rich Languages
  di: Zakershahrak, Mehrdad, et al.
  Pubblicazione: (2025)
• SumRecom: A Personalized Summarization Approach by Learning from Users' Feedback
  di: Ghodratnama, Samira, et al.
  Pubblicazione: (2024)
• Debate Helps Weak-to-Strong Generalization
  di: Lang, Hao, et al.
  Pubblicazione: (2025)
• Interpretable by Design: Query-Specific Neural Modules for Explainable Reinforcement Learning
  di: Zakershahrak, Mehrdad
  Pubblicazione: (2025)
• Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation
  di: Zou, Deyu, et al.
  Pubblicazione: (2025)