Can We Trust the Judges? Validation of Factuality Evaluation Methods via Answer Perturbation

• URL: http://arxiv.org/abs/2609.15561v1
• Date: Mon, 14 Sep 2026 13:41:35 GMT
• Title: Can We Trust the Judges? Validation of Factuality Evaluation Methods via Answer Perturbation
• Abstract summary: Despite the rise of factuality-based metrics, their sensitivity and reliability remain underexplored.<n>This paper introduces a meta-evaluation framework that systematically tests these metrics using controlled corruptions of gold standard answers.<n>Our method generates ranked outputs with known degrees of degradation to probe how metrics capture nuanced changes in truthfulness.
• Score: 12.630110640940316
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating the factual correctness of large language models (LLMs) is vital for many applications. But are our evaluation tools themselves trustworthy? Despite the rise of factuality-based metrics, their sensitivity and reliability remain underexplored. This paper introduces a meta-evaluation framework that systematically tests these metrics using controlled corruptions of gold standard answers. Our method generates ranked outputs with known degrees of degradation to probe how metrics capture nuanced changes in truthfulness. Our experiments reveal that pipeline-based methods, such as the RAGAS's factual correctness metric, better track degradation than LLM-as-judge approaches. We also propose a new variant of the factual correctness metric that provides a competitive and cost-efficient.

Related papers

• Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models [54.51264434040939]
  Uncertainty estimation (UE) aims to detect hallucinated outputs of large language models (LLMs)<n>We formalise this phenomenon as proxy failure, since most UE metrics originate from model behaviour.<n>We propose Truth AnChoring (TAC), a post-hoc calibration method to remedy UE metrics.
  arXiv  Detail & Related papers  (2026-04-01T03:42:16Z)
• 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)
• Calibration Is Not Enough: Evaluating Confidence Estimation Under Language Variations [49.84786015324238]
  Confidence estimation (CE) indicates how reliable the answers of large language models (LLMs) are, and can impact user trust and decision-making.<n>We present a comprehensive evaluation framework for CE that measures their confidence quality on three new aspects.<n>These include robustness of confidence against prompt perturbations, stability across semantic equivalent answers, and sensitivity to semantically different answers.
  arXiv  Detail & Related papers  (2026-01-12T23:16:50Z)
• All Claims Are Equal, but Some Claims Are More Equal Than Others: Importance-Sensitive Factuality Evaluation of LLM Generations [57.8036236269546]
  Existing methods for evaluating the factuality of large language model (LLM) responses treat all claims as equally important.<n>This results in misleading evaluations when vital information is missing or incorrect as it receives the same weight as peripheral details.<n>We introduce VITAL, a set of metrics that provide greater sensitivity in measuring the factuality of responses by incorporating the relevance and importance of claims with respect to the query.
  arXiv  Detail & Related papers  (2025-10-08T14:40:33Z)
• MetaFaith: Faithful Natural Language Uncertainty Expression in LLMs [66.14178164421794]
  We introduce MetaFaith, a novel prompt-based calibration approach inspired by human metacognition.<n>We show that MetaFaith robustly improves faithful calibration across diverse models and task domains, enabling up to 61% improvement in faithfulness.
  arXiv  Detail & Related papers  (2025-05-30T17:54:08Z)
• MCQA-Eval: Efficient Confidence Evaluation in NLG with Gold-Standard Correctness Labels [16.300463494913593]
  Large Language Models (LLMs) require robust confidence estimation.<n>McQCA-Eval is an evaluation framework for assessing confidence measures in Natural Language Generation.
  arXiv  Detail & Related papers  (2025-02-20T05:09:29Z)
• Do Automatic Factuality Metrics Measure Factuality? A Critical Evaluation [16.506990103937515]
  We stress test a range of automatic factuality metrics to probe what they actually capture.<n>We find that all metrics show substantial performance drops on the latter.<n>Some metrics are more sensitive to benign, fact-preserving edits than to factual corrections.
  arXiv  Detail & Related papers  (2024-11-25T18:15:15Z)
• Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators [6.403926452181712]
  Large Language Models (LLMs) tend to be unreliable in the factuality of their answers. We present a survey and empirical comparison of estimators of factual confidence. Our experiments indicate that trained hidden-state probes provide the most reliable confidence estimates.
  arXiv  Detail & Related papers  (2024-06-19T10:11:37Z)
• TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness [58.721012475577716]
  Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, prompting a surge in their practical applications. This paper introduces TrustScore, a framework based on the concept of Behavioral Consistency, which evaluates whether an LLMs response aligns with its intrinsic knowledge.
  arXiv  Detail & Related papers  (2024-02-19T21:12:14Z)
• GO FIGURE: A Meta Evaluation of Factuality in Summarization [131.1087461486504]
  We introduce GO FIGURE, a meta-evaluation framework for evaluating factuality evaluation metrics. Our benchmark analysis on ten factuality metrics reveals that our framework provides a robust and efficient evaluation. It also reveals that while QA metrics generally improve over standard metrics that measure factuality across domains, performance is highly dependent on the way in which questions are generated.
  arXiv  Detail & Related papers  (2020-10-24T08:30:20Z)

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.