← Back to all news
arXiv Computation and Language By Hongli Zhou, Hui Huang, Rui Zhang, Kehai Chen, Bing Xu, Conghui Zhu, Tiejun Zhao, Muyun Yang

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

Read the original on arXiv Computation and Language →

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.

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 Machine Learning
4d ago

Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration

The paper investigates how large language models (LLMs) used as judges in absolute scoring tasks exhibit systematic biases that compromise reliability. It shows that a judge’s task accuracy strongly predicts both its judging accuracy and its directional bias, yet more capable examinee models consistently receive more lenient judgments. To mitigate these biases, the authors propose a calibrated weighted majority voting (WMV) ensemble that estimates judges’ error rates from inter-judge agreement patterns, achieving near-oracle performance without labeled data and improving both accuracy and fairness.

By Gemma Zhang, Prachi Badarayani, Asmi Kumar, Sadid Hasan, Sulaiman Vesal
llmsbenchmarkssafety
More like this →
arXiv Computation and Language
Aug 28

JudgeStealer: Extracting LLM Judging Capabilities across Evaluation Protocols

JudgeStealer is a query‑efficient framework that extracts the judging capabilities of large language models across pointwise scoring, pairwise comparison, and listwise ranking protocols. It leverages cross‑protocol agreement to convert pointwise scores into higher‑order supervision, dynamically selects informative inputs, and applies score smoothing and multi‑protocol review to preserve ordinal structure and avoid catastrophic forgetting. Experiments show it outperforms existing baselines, achieving up to 73.3% accuracy on pointwise, 87.0% on pairwise, and 71.6% on listwise evaluation, while remaining robust against common extraction defenses.

By Chen Chen, Yaolin Chen, Xuehan Sun, Juan Lin, Xueluan Gong, Yuhang Zheng, Qian Wang, Kwok-Yan Lam
llmsbenchmarks
More like this →