arXiv AI
Jul 23
Self-Preference Bias in Rubric-Based Evaluation of Large Language Models
arXiv:2604. 06996v2 Announce Type: replace-cross Abstract: LLM-as-a-judge has become the de facto approach for evaluating LLM outputs.
Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge
Related stories
arXiv AI
Sep 15
Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges
arXiv:2602.13576v2 Announce Type: replace-cross Abstract: Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-langu...
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.
arXiv Computation and Language
Sep 1
Small Language Models as Judges for Rubric-Based Reinforcement Learning
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...
arXiv Machine Learning
Sep 14
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.
arXiv AI
2d ago
Prompt Lottery in LLM-as-a-Judge: Measuring and Mitigating Sensitivity to Syntactic Rephrasing
The paper introduces the "Prompt Lottery" phenomenon, where paraphrastic rephrasings of judge prompts in LLM-as-a-Judge (LLMaJ) lead to inconsistent judgments and can even reverse model rankings. A large-scale study across various tasks, judge families, and model backbones demonstrates that these prompt variations significantly alter evaluation outcomes. A user study shows that LLMaJ judges are 6–9 times more sensitive to prompt rephrasings than humans, and that aggregating multiple prompts improves robustness by focusing on consistent judgments.
arXiv AI
Oct 15
A CaLLM Judge is a Better Judge: Mitigating Bias in LLM-as-a-judge
arXiv:2610.18108v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as judges to predict which of two candidate answers a human evaluator would prefer, providing a sc...
arXiv AI
Sep 30
PADM\'E: Preference Alignment Data Synthesis for Meta-Evaluation of LM Agent Evaluators
PADM'E is a method for synthesizing preference‑aligned data to meta‑evaluate language‑model (LM) evaluators of agentic behaviors. It reframes meta‑evaluation as a preference judgment problem, generating criterion‑based data with small LMs and no human involvement. In a prototype, PADM'E produced 1,000 samples across four domains and three criteria, and human validation showed agreement with human judgment rising from 73% to 85% compared to a naive baseline.
arXiv Machine Learning
Jun 15
From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation
arXiv:2606. 13221v2 Announce Type: replace Abstract: Evaluating new large language models typically requires costly human annotation campaigns at scale.
arXiv Computation and Language
6d ago
Understanding Jev-Style System One Models: Does Structure Reduce Selection Bias?
arXiv:2610.35826v1 Announce Type: new Abstract: Selection bias in large language models (LLMs) can persist despite instructions to ignore presentation order or prompts that elicit reasoning. Recent e...
arXiv AI
Oct 21
PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges
arXiv:2605.30803v2 Announce Type: replace Abstract: LLM judges are increasingly used to evaluate open-ended responses, but their scores depend strongly on the rubrics that condition them. A vague rub...
arXiv AI
Aug 18
Mitigating Rubric Interference in LLM Judges via On-Policy Self-Distillation
arXiv:2608. 14684v1 Announce Type: cross Abstract: LLM judges increasingly evaluate responses against fine-grained rubric checklists.