Rater State Bias in RLHF Preference Data: An Audit Framework

arXiv:2605.06895v1 Announce Type: new Abstract: How can we make models robust to even imperfect human feedback? In reinforcement learning from human feedback (RLHF), human

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: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:2603.22813v1 Announce Type: new Abstract: Humans often juggle multiple, sometimes conflicting objectives and shift their priorities as circumstances change, rather than

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:2605.01604v1 Announce Type: new Abstract: Existing evaluation frameworks for large language models -- including HELM, MT-Bench, AgentBench, and BIG-bench -- are designed for

arXiv:2605.06890v1 Announce Type: new Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures

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