Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges

• URL: http://arxiv.org/abs/2601.20913v1
• Date: Wed, 28 Jan 2026 18:05:06 GMT
• Title: Noisy but Valid: Robust Statistical Evaluation of LLMs with Imperfect Judges
• Authors: Chen Feng, Minghe Shen, Ananth Balashankar, Carsten Gerner-Beuerle, Miguel R. D. Rodrigues,
• Abstract summary: We introduce a "Noisy but Valid" hypothesis testing framework to address this.<n>Our framework theoretically guarantees finite-sample Type-I error control (validity) despite calibration uncertainty.
• Score: 14.256638949961063
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reliable certification of Large Language Models (LLMs)-verifying that failure rates are below a safety threshold-is critical yet challenging. While "LLM-as-a-Judge" offers scalability, judge imperfections, noise, and bias can invalidate statistical guarantees. We introduce a "Noisy but Valid" hypothesis testing framework to address this. By leveraging a small human-labelled calibration set to estimate the judge's True Positive and False Positive Rates (TPR/FPR), we derive a variance-corrected critical threshold applied to a large judge-labelled dataset. Crucially, our framework theoretically guarantees finite-sample Type-I error control (validity) despite calibration uncertainty. This distinguishes our work from Prediction-Powered Inference (PPI), positioning our method as a diagnostic tool that explicitly models judge behavior rather than a black-box estimator. Our contributions include: (1) Theoretical Guarantees: We derive the exact conditions under which noisy testing yields higher statistical power than direct evaluation; (2) Empirical Validation: Experiments on Jigsaw Comment, Hate Speech and SafeRLHF confirm our theory; (3) The Oracle Gap: We reveal a significant performance gap between practical methods and the theoretical "Oracle" (perfectly known judge parameters), quantifying the cost of estimation. Specifically, we provide the first systematic treatment of the imperfect-judge setting, yielding interpretable diagnostics of judge reliability and clarifying how evaluation power depends on judge quality, dataset size, and certification levels. Together, these results sharpen understanding of statistical evaluation with LLM judges, and highlight trade-offs among competing inferential tools.

Related papers

• Judge Reliability Harness: Stress Testing the Reliability of LLM Judges [1.1699027359021665]
  Judge Reliability Harness is an open source library for constructing validation suites that test the reliability of LLM judges.<n>We evaluate four state-of-the-art judges across four benchmarks spanning safety, persuasion, misuse, and agentic behavior.
  arXiv  Detail & Related papers  (2026-03-05T17:27:07Z)
• Who can we trust? LLM-as-a-jury for Comparative Assessment [42.32900791516691]
  Large language models (LLMs) are increasingly applied as automatic evaluators for natural language generation assessment.<n>LLMs judges vary substantially in performance across tasks and aspects, and their judgment probabilities may be biased and inconsistent.<n>We propose BT-sigma, a judge-aware extension of the Bradley-Terry model that introduces a discriminator parameter for each judge to jointly infer item rankings and judge reliability from pairwise comparisons alone.
  arXiv  Detail & Related papers  (2026-02-18T17:04:02Z)
• On Calibration of Large Language Models: From Response To Capability [66.59139960234326]
  Large language models (LLMs) are widely deployed as general-purpose problem solvers.<n>We introduce capability calibration, which targets the model's expected accuracy on a query.<n>Our results demonstrate that capability-calibrated confidence improves pass@$k$ prediction and inference budget allocation.
  arXiv  Detail & Related papers  (2026-02-14T01:07:45Z)
• A Judge-Aware Ranking Framework for Evaluating Large Language Models without Ground Truth [4.9467757325435775]
  evaluating large language models (LLMs) on open-ended tasks is increasingly done via the LLM-as-a-judge paradigm.<n>Treating all judges equally can yield biased leaderboards and misleading uncertainty estimates.<n>We propose a judge-aware ranking framework that extends the Bradley-Terry-Luce model by introducing judge-specific discrimination parameters.
  arXiv  Detail & Related papers  (2026-01-29T15:01:28Z)
• Empirical Likelihood-Based Fairness Auditing: Distribution-Free Certification and Flagging [18.71249153088185]
  Machine learning models in high-stakes applications, such as recidivism prediction and automated personnel selection, often exhibit systematic performance disparities.<n>We propose a novel empirical likelihood-based (EL) framework that constructs robust statistical measures for model performance disparities.
  arXiv  Detail & Related papers  (2026-01-28T05:36:19Z)
• Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation [25.80946316489521]
  We introduce linear probes trained with a Brier score-based loss to provide calibrated uncertainty estimates from reasoning judges' hidden states.<n>We evaluate our approach on both objective tasks (reasoning, mathematics, factuality, coding) and subjective human preference judgments.
  arXiv  Detail & Related papers  (2025-12-23T22:08:46Z)
• TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them [58.04324690859212]
  Large Language Models (LLMs) as automated evaluators (LLM-as-a-judge) has revealed critical inconsistencies in current evaluation frameworks.<n>We identify two fundamental types of inconsistencies: Score-Comparison Inconsistency and Pairwise Transitivity Inconsistency.<n>We propose TrustJudge, a probabilistic framework that addresses these limitations through two key innovations.
  arXiv  Detail & Related papers  (2025-09-25T13:04:29Z)
• CompassJudger-2: Towards Generalist Judge Model via Verifiable Rewards [72.44810390478229]
  CompassJudger-2 is a novel generalist judge model that overcomes limitations via a task-driven, multi-domain data curation strategy.<n> CompassJudger-2 achieves superior results across multiple judge and reward benchmarks.
  arXiv  Detail & Related papers  (2025-07-12T01:34:24Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Is Your Model Fairly Certain? Uncertainty-Aware Fairness Evaluation for LLMs [7.197702136906138]
  We propose an uncertainty-aware fairness metric, UCerF, to enable a fine-grained evaluation of model fairness.<n> observing data size, diversity, and clarity issues in current datasets, we introduce a new gender-occupation fairness evaluation dataset.<n>We establish a benchmark, using our metric and dataset, and apply it to evaluate the behavior of ten open-source AI systems.
  arXiv  Detail & Related papers  (2025-05-29T20:45:18Z)
• FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees [41.78390564658645]
  Large Language Models (LLMs) to generate hallucinations and non-factual content undermines their reliability in high-stakes domains. We introduce FactTest, a novel framework that statistically assesses whether a LLM can confidently provide correct answers to given questions. We show that FactTest effectively detects hallucinations and improves the model's ability to abstain from answering unknown questions, leading to an over 40% accuracy improvement.
  arXiv  Detail & Related papers  (2024-11-04T20:53:04Z)
• Equal Opportunity of Coverage in Fair Regression [50.76908018786335]
  We study fair machine learning (ML) under predictive uncertainty to enable reliable and trustworthy decision-making. We propose Equal Opportunity of Coverage (EOC) that aims to achieve two properties: (1) coverage rates for different groups with similar outcomes are close, and (2) the coverage rate for the entire population remains at a predetermined level.
  arXiv  Detail & Related papers  (2023-11-03T21:19:59Z)
• Binary Classification with Confidence Difference [100.08818204756093]
  This paper delves into a novel weakly supervised binary classification problem called confidence-difference (ConfDiff) classification. We propose a risk-consistent approach to tackle this problem and show that the estimation error bound the optimal convergence rate. We also introduce a risk correction approach to mitigate overfitting problems, whose consistency and convergence rate are also proven.
  arXiv  Detail & Related papers  (2023-10-09T11:44:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.