← Back to all news
arXiv Computation and Language By Guiquan Sun, Bing Bai, Martin Renqiang Min, Dongjin Song

Judging the Justification: Decision Certificate Supervision for Generative Reward Models

Read the original on arXiv Computation and Language →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computation and Language
Sep 16

Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization

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
llmsreinforcement-learningbenchmarkssafety
More like this →
arXiv AI
Oct 16

Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM Evaluation

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
llmsreinforcement-learningsafety
More like this →
Hugging Face Trending Papers
Jul 2

Many Voices, One Reward: Multi-Role Rubric Generation for LLM Judging and Reward Modeling

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.

llmsreinforcement-learningbenchmarks
More like this →