HIPPO: Enhancing the Table Understanding Capability of LLMs through Hybrid-Modal Preference Optimization

Documenti analoghi

• Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
  di: Li, Xinze, et al.
  Pubblicazione: (2024)
• ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization
  di: Jin, Zhensheng, et al.
  Pubblicazione: (2025)
• COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis
  di: Yang, Weiqing, et al.
  Pubblicazione: (2024)
• RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts
  di: Wu, Mingyan, et al.
  Pubblicazione: (2025)
• Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
  di: Duan, Shaohua, et al.
  Pubblicazione: (2025)