Mitigating Cognitive Bias in RLHF by Altering Rationality

arXiv:2603.22829v1 Announce Type: new Abstract: With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted

arXiv:2607.16195v1 Announce Type: new Abstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to

arXiv:2603.18736v1 Announce Type: cross Abstract: Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models, current reward modeling

arXiv:2604.26233v1 Announce Type: new Abstract: As Large Language Models (LLMs) are proposed as legal decision assistants, and even first-instance decision-makers, across a range

arXiv:2610.21138v1 Announce Type: new Abstract: Feedback noise is pervasive in preference data, arising from subjective human judgments, annotation mistakes, and imperfect LLM

arXiv:2606.27578v1 Announce Type: cross Abstract: Reward models for Reinforcement Learning from Human Feedback (RLHF) pool preferences across thousands of annotators and fit one

arXiv:2606.27580v1 Announce Type: cross Abstract: Reinforcement learning from human feedback (RLHF) in production does not always have a synchronous reward signal. Code-execution

arXiv:2605.04077v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation