arXiv:2604. 26360v2 Announce Type: replace-cross Abstract: Reinforcement learning from human feedback (RLHF) systems face a compounding alignment challenge: not only are learned reward models uncertain about unseen state-action pairs, but the human preference annotations they are trained on are themselves inconsistent, context-dependent, and noisy.
By Disha Singha
arXiv:2605. 00155v3 Announce Type: replace Abstract: Reinforcement learning from human feedback (RLHF) is a central post-training tool for aligning large language models, but its training reward is only a learned proxy for true human utility.
By Yikai Wang, Shang Liu, Jose Blanchet
arXiv:2606. 03962v1 Announce Type: cross Abstract: Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward.
By Anthony GX-Chen, Ankit Anand, Gheorghe Comanici, Zaheer Abbas, Eser Ayg\"un, David Smalling, Shibl Mourad, Doina Precup, Andr\'e Barreto, Mark Rowland
arXiv:2609.38938v1 Announce Type: new
Abstract: Reinforcement learning with human feedback (RLHF) learns from human comparisons, which can be corrupted or deliberately manipulated. This paper studies...
By Xinyi Ni, Lifeng Lai
arXiv:2606. 19818v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) aligns large language models by training reward models on preference data and optimizing policies to maximize predicted rewards.
By Licheng Pan, Haocheng Yang, Haoxuan Li, Yichen Sun, Yunsheng Lu, Shijian Wang, Lei Shen, Yuan Lu, Zhixuan Chu, Hao Wang
arXiv:2606. 03238v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) makes large-scale post-training possible by replacing an underspecified human objective with learned and scalable proxies.
By Zelalem Abahana