alphaXiv

Explore

State of the Art

Sign In

Labs

Feedback

Browser Extension

We're hiring
PaperBlogResources

Information-Theoretic Reward Decomposition for Generalizable RLHF

BibTex
Copy
@misc{maoFri Oct 24 2025 07:58:50 GMT+0000 (Coordinated Universal Time)informationtheoreticrewarddecomposition,
      title={Information-Theoretic Reward Decomposition for Generalizable RLHF},
      author={Liyuan Mao and Haoran Xu and Amy Zhang and Weinan Zhang and Chenjia Bai},
      year={Fri Oct 24 2025 07:58:50 GMT+0000 (Coordinated Universal Time)},
      eprint={2504.06020},
      archivePrefix={arXiv},
      primaryClass={cs.AI},
      url={https://arxiv.org/abs/2504.06020},
}
Transform this paper into an audio lecture
Get an engaging lecture and Q&A format to quickly understand the paper in minutes, perfect for learning on the go.
Audio lecture
Q&A format