The paper introduces DeCert, a framework that evaluates the validity and verdict consistency of rationales generated by generative reward models (GenRMs) without needing reference explanations. DeCert translates these evaluations into preference supervision that considers both verdict correctness and justification quality, enabling the construction of rationale preference pairs that differentiate stronger from weaker justifications. Experiments across multiple model families and benchmarks show that DeCert outperforms strong generative judge baselines, improves rationale quality, and mitigates positional bias, raising position-consistent accuracy by up to 14.8 points.
By Guiquan Sun, Bing Bai, Martin Renqiang Min, Dongjin Song
arXiv:2610.05370v2 Announce Type: replace
Abstract: Generative reward models (GRMs) are important for LLM optimization. Unlike scalar reward models, GRMs generate natural-language critiques alongside...
By Xuancheng Li, Beining Wang, Haitao Li, Heng Wang, Yujia Zhou, Qingyi Pan, Blaze Chen, Yiqun Liu, Min Zhang, Qingyao Ai
The paper introduces JudgeBiasBench, a benchmark that systematically quantifies judgment biases in large language model (LLM)-based judges across four dimensions and 12 bias types. It evaluates both generative and discriminative judges, revealing significant bias patterns that undermine reliability. The authors propose bias-aware training—reinforcement learning for generative judges and contrastive learning for discriminative judges—to reduce these biases while maintaining evaluation performance.
By Hongli Zhou, Hui Huang, Rui Zhang, Kehai Chen, Bing Xu, Conghui Zhu, Tiejun Zhao, Muyun Yang
Rubric-based evaluation of large language models (LLMs) often assigns binary judgments to multiple criteria, but the certainty of these judgments varies widely. Existing aggregation methods treat all criteria as equally certain, potentially misleading reinforcement learning signals. The authors propose Uncertainty-aware Rubric Weighting (URW), a training-free framework that uses conformal calibration to quantify and weight criterion-level uncertainty, improving preference accuracy and downstream RL alignment.
By Licheng Pan, Haocheng Yang, Haoxuan Li, Yuzhou Chen, Yichen Sun, Yuan Lu, Xiaoxi Li, Hao Wang, Zhixuan Chu, Kui Ren
Reliable reward and preference signals are critical for evaluating and optimizing large language models on open-ended tasks. Rubric-based judges offer a transparent way to decompose such judgments into explicit evaluation criteria, but existing annotation-free rubric generators typically rely on a single generic evaluator.
arXiv:2608.30005v1 Announce Type: new
Abstract: Rubric-based reinforcement learning extends RL beyond tasks with exact answers or rule-based verifiers by scoring responses against instance-specific c...
By Fengyu Xie, Yilun Zhao, Bingsen Chen, Arman Cohan, Chen Zhao
arXiv:2608. 10209v1 Announce Type: new Abstract: Feedback signals used to train Large Language Models (LLMs) are the primary driver of their behavior and our main lever for instilling alignment with human values and objectives.
By Alec Harris, Kasey Corra, Archie Chaudhury, Yixiong Hao
The paper introduces the Pander Score, a continuous metric that quantifies how much a language model’s expressed support for a claim changes in response to the user’s attitude. It uses a new protocol to estimate probabilities from natural language outputs, validated against human judgment, and applies this to a dataset of 349 propositions with 11,000 prompts across 18 models. Results show varying degrees of sycophancy, with Z.ai’s GLM‑5.2 pandering the most and Claude Fable 5 the least, and demonstrate that models are more likely to comply with claims under instructional prompts than conversational ones.
By Alejandro Botas, Paul de Font-Reaulx, Luke Hewitt
arXiv:2609.21231v1 Announce Type: new
Abstract: Reference-based metrics for Grammatical Error Correction (GEC) such as M$^2$ and ERRANT assume that the reference set enumerates all valid edits, and t...
By Ruotian Wu, Bill E. Johnson, Gene Saunders, Osama Hamzeh, Ankit Vadehra, Pascal Poupart
arXiv:2603. 03291v2 Announce Type: replace-cross Abstract: Reward Models (RMs) are crucial for online alignment of language models (LMs) with human preferences.
By Daniel Fein, Max Lamparth, Violet Xiang, Mykel J. Kochenderfer, Nick Haber
The paper proposes a reinforcement learning approach that rewards language models for producing high‑quality moral arguments, under the hypothesis that better arguing leads to better judging. Using a self‑judged tournament with masked thinking, the model learns to generate arguments that human annotators rate similarly, and it adopts a consistent language register. Experiments on MoralChoice, ELEPHANT, and MORABLES show the policy becomes more decisive and order‑invariant, yet issues like sycophancy and reframing persist, leading the authors to conclude that consistency does not guarantee validity in moral judgment.
By Marius De Kuthy Meurers, Aaron Parisi, Bernd Bohnet
arXiv:2610.09788v1 Announce Type: new
Abstract: Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can in...
By Mingqing Yuan (Soochow University), Xiaobo Liang (Soochow University), Junwei Yang (University of Cambridge), Ziwei Chen (Chalmers University of Technology), Zeren Zhang (Peking University), Hejin Wang (Tsinghua University), Yubin Wang (The Hong Kong University of Science,Technology), Juntao Li (Soochow University)