BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment

Documenti analoghi

• BPO: Revisiting Preference Modeling in Direct Preference Optimization
  di: Sun, Lin, et al.
  Pubblicazione: (2025)
• Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
  di: Tong, Yongqi, et al.
  Pubblicazione: (2024)
• Optimizing Language Model's Reasoning Abilities with Weak Supervision
  di: Tong, Yongqi, et al.
  Pubblicazione: (2024)
• BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment
  di: Xu, Wenda, et al.
  Pubblicazione: (2024)
• KGHaluBench: A Knowledge Graph-Based Hallucination Benchmark for Evaluating the Breadth and Depth of LLM Knowledge
  di: Robertson, Alex, et al.
  Pubblicazione: (2026)