Lignende værker

• DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs
  af: Liu, Zhihan, et al.
  Udgivet: (2024)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
  af: Liu, Zhihan, et al.
  Udgivet: (2024)
• $\mathbf{(N,K)}$-Puzzle: A Cost-Efficient Testbed for Benchmarking Reinforcement Learning Algorithms in Generative Language Model
  af: Zhang, Yufeng, et al.
  Udgivet: (2024)
• Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
  af: Liu, Zhihan, et al.
  Udgivet: (2023)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment
  af: Zhang, Shenao, et al.
  Udgivet: (2024)