VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation

• URL: http://arxiv.org/abs/2604.25235v2
• Date: Wed, 29 Apr 2026 07:06:15 GMT
• Title: VLM Judges Can Rank but Cannot Score: Task-Dependent Uncertainty in Multimodal Evaluation
• Abstract summary: Vision-language models (VLMs) are increasingly used as automated judges for multimodal systems, yet their scores provide no indication of reliability.<n>We study this problem through conformal prediction, a distribution-free framework that converts a judge's point score into a calibrated prediction interval.<n>We present the first systematic analysis of conformal prediction for VLM-as-a-Judge across 3 judges and 14 visual task categories.
• Score: 4.694504497452662
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language models (VLMs) are increasingly used as automated judges for multimodal systems, yet their scores provide no indication of reliability. We study this problem through conformal prediction, a distribution-free framework that converts a judge's point score into a calibrated prediction interval using only score-token log-probabilities, with no retraining. We present the first systematic analysis of conformal prediction for VLM-as-a-Judge across 3 judges and 14 visual task categories. Our results show that evaluation uncertainty is strongly task-dependent: intervals cover ~40% of the score range for aesthetics and natural images but expand to ~70% for chart and mathematical reasoning, yielding a quantitative reliability map for multimodal evaluation. We further identify a failure mode not captured by standard evaluation metrics, ranking-scoring decoupling, where judges achieve high ranking correlation while producing wide, uninformative intervals, correctly ordering responses but failing to assign reliable absolute scores. Finally, we show that interval width is driven primarily by task difficulty and annotation quality, i.e., the same judge and method yield 4.5x narrower intervals on a clean, multi-annotator captioning benchmark. Code: https://github.com/divake/VLM-Judge-Uncertainty

Related papers

• Can We Trust LLM Judges: A Study of Capability-Dependent Biases and Multi-Judge Ensemble for Bias Calibration [0.5294698352039444]
  We study absolute scoring tasks, which mirror more realistic use cases.<n>We show that a model's task accuracy strongly predicts its judging accuracy.<n>More capable examinee models consistently receive more lenient judgments from all judges.
  arXiv  Detail & Related papers  (2026-09-10T00:25:39Z)
• C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning [0.6138671548064355]
  Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning.<n>We introduce C2-Faith, a benchmark that targets two complementary dimensions of faithfulness: causality (does each step logically follow from prior context?) and coverage.<n>We evaluate three frontier judges under three tasks: binary causal detection, causal step localization, and coverage scoring.
  arXiv  Detail & Related papers  (2026-03-05T13:36:47Z)
• Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics [25.374192139098284]
  We study prototypicality bias as a systematic failure mode in multimodal evaluation.<n>We introduce a controlled contrastive benchmark ProtoBias, spanning Animals, Objects, and Demography images.<n>Our results show that widely used metrics, including CLIPScore, PickScore, and VQA-based scores, frequently misrank these pairs.<n>We propose ProtoScore, a robust 7B- parameter metric that substantially reduces failure rates and suppresses misranking.
  arXiv  Detail & Related papers  (2026-01-08T13:49:14Z)
• Reference-Free Rating of LLM Responses via Latent Information [53.463883683503106]
  We study the common practice of asking a judge model to assign Likert-scale scores to free-text responses.<n>We then propose and evaluate Latent Judges, which derive scalar ratings from internal model signals.<n>Across a broad suite of pairwise and single-rating benchmarks, latent methods match or surpass standard prompting.
  arXiv  Detail & Related papers  (2025-09-29T12:15:52Z)
• 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)
• When Judgment Becomes Noise: How Design Failures in LLM Judge Benchmarks Silently Undermine Validity [21.192000569821943]
  We argue that without tight objectives and verifiable constructions, benchmark rankings can produce high-confidence rankings that are in fact largely noise.<n>We show that the ELO-style aggregation used by Arena-Hard Auto collapses and masks genuine ranking uncertainty.<n>Our results highlight design failures that undermine validity and offer actionable principles for building better-scoped, reliability-aware benchmarks.
  arXiv  Detail & Related papers  (2025-09-24T16:26:47Z)
• Judging LLMs on a Simplex [2.088672652658465]
  A common practice is to use large language models (LLMs) themselves as judges, but the theoretical properties of this approach are not yet well understood.<n>We show that a geometric framework that represents both judges and candidates as points on a probability simplex can provide helpful insight on what is or is not identifiable.
  arXiv  Detail & Related papers  (2025-05-28T04:50:41Z)
• SureMap: Simultaneous Mean Estimation for Single-Task and Multi-Task Disaggregated Evaluation [75.56845750400116]
  Disaggregated evaluation -- estimation of performance of a machine learning model on different subpopulations -- is a core task when assessing performance and group-fairness of AI systems. We develop SureMap that has high estimation accuracy for both multi-task and single-task disaggregated evaluations of blackbox models. Our method combines maximum a posteriori (MAP) estimation using a well-chosen prior together with cross-validation-free tuning via Stein's unbiased risk estimate (SURE)
  arXiv  Detail & Related papers  (2024-11-14T17:53:35Z)
• Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2) [62.44395685571094]
  We introduce T2IScoreScore, a curated set of semantic error graphs containing a prompt and a set of increasingly erroneous images. These allow us to rigorously judge whether a given prompt faithfulness metric can correctly order images with respect to their objective error count. We find that the state-of-the-art VLM-based metrics fail to significantly outperform simple (and supposedly worse) feature-based metrics like CLIPScore.
  arXiv  Detail & Related papers  (2024-04-05T17:57:16Z)
• Bipartite Ranking Fairness through a Model Agnostic Ordering Adjustment [54.179859639868646]
  We propose a model agnostic post-processing framework xOrder for achieving fairness in bipartite ranking. xOrder is compatible with various classification models and ranking fairness metrics, including supervised and unsupervised fairness metrics. We evaluate our proposed algorithm on four benchmark data sets and two real-world patient electronic health record repositories.
  arXiv  Detail & Related papers  (2023-07-27T07:42:44Z)
• Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting [56.44300325295678]
  We propose a novel count interval partition criterion called Uniform Error Partition (UEP) MCP criterion selects the best count proxy for each interval to represent its count value during inference. We propose a simple yet effective model termed Uniform Error Partition Network (UEPNet)
  arXiv  Detail & Related papers  (2021-07-27T06:24:15Z)

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.