2D-DPO: Scaling Direct Preference Optimization with 2-Dimensional Supervision

Documenti analoghi

• Can Large Language Models Detect Errors in Long Chain-of-Thought Reasoning?
  di: He, Yancheng, et al.
  Pubblicazione: (2025)
• Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation
  di: Gu, Jihao, et al.
  Pubblicazione: (2024)
• GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models
  di: Li, Shilong, et al.
  Pubblicazione: (2024)
• Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models
  di: He, Yancheng, et al.
  Pubblicazione: (2024)
• 2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization
  di: Li, Mengyang, et al.
  Pubblicazione: (2025)