@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.