Enhancing Multi-Step Reasoning Abilities of Language Models through Direct Q-Function Optimization

Documenti analoghi

• Process Supervision-Guided Policy Optimization for Code Generation
  di: Dai, Ning, et al.
  Pubblicazione: (2024)
• Flaming-hot Initiation with Regular Execution Sampling for Large Language Models
  di: Chen, Weizhe, et al.
  Pubblicazione: (2024)
• Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization
  di: Liu, Jiacai, et al.
  Pubblicazione: (2024)
• Self-Play Preference Optimization for Language Model Alignment
  di: Wu, Yue, et al.
  Pubblicazione: (2024)
• Reinforcement Learning from Human Feedback with Active Queries
  di: Ji, Kaixuan, et al.
  Pubblicazione: (2024)