Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

• URL: http://arxiv.org/abs/2606.02578v1
• Date: Mon, 01 Jun 2026 17:59:46 GMT
• Title: Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling
• Abstract summary: MLLM judges tend to reward plausible narratives over perceptually correct answers when visual evidence conflicts with textual cues.<n>We introduce the Perceptually Perturbed Judgment dataset, which constructs minimally edited counterfactual responses.<n>We develop a unified training framework that combines a structured GRPO-based reward with a batch-ranking objective, achieving coherent global ordering without explicit pairwise labels.
• Score: 35.945096782147864
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical weakness: when visual evidence conflicts with textual cues, MLLM judges tend to reward plausible narratives over perceptually correct answers. We identify and systematically analyze this phenomenon, which we term Perceptual Judgment Bias. Through controlled visual perturbations, existing multimodal judges frequently anchor on the response text instead of their own visual perception, leading to inconsistent and non-verifiable evaluations. To address this issue, we introduce the Perceptually Perturbed Judgment Dataset, which constructs minimally edited counterfactual responses that isolate perceptual errors and enable verifiable supervision. Building on this dataset, we develop a unified training framework that combines a structured GRPO-based reward with a batch-ranking objective, achieving coherent global ordering without explicit pairwise labels. Experiments across diverse MLLM-as-a-Judge benchmarks show that our approach substantially improves perceptual fidelity, ranking coherence, and alignment with human evaluation. Our results establish a scalable and generalizable pathway for training multimodal judges that are perceptually grounded, interpretable, and robust to visual-reasoning conflicts.

Related papers

• On the Adversarial Robustness of Multimodal LLM Judges [49.80009278197918]
  We introduce RobustMLLMJudge, the first framework for evaluating the adversarial robustness of general-purpose MLLMs when functioning as judges.<n>Using RobustMLLMJudge, we reveal that different MLLM judges are highly vulnerable to score-inflating adversarial attacks.<n>We propose MGSIA, a novel method that bypasses these constraints to enable more effective and transferable attacks on MLLM judges.
  arXiv  Detail & Related papers  (2026-06-14T05:30:20Z)
• Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games [20.896576101848655]
  We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating.<n>We instantiate the framework as a benchmark of 474 executable games, each evaluated under five fixed configuration search spaces corresponding to five difficulty levels.<n>Results show that the benchmark is highly discriminative, exposing large differences not only in success rate but also in interaction efficiency.
  arXiv  Detail & Related papers  (2026-05-26T09:12:30Z)
• Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents? [61.49434544687523]
  We introduce REFLECT, a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments.<n> REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions.<n>Our experiments show that even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures.
  arXiv  Detail & Related papers  (2026-05-18T23:55:08Z)
• GRASP: Deterministic argument ranking in interaction graphs [65.66879897437157]
  We show that holistic judging suffers from substantial inter-model disagreement.<n>This instability arises from collapsing a debate's complex interaction structure into a single opaque score.<n>We propose GRASP, a deterministic framework that aggregates stable local interaction judgments into a global ranking.
  arXiv  Detail & Related papers  (2026-05-18T21:49:02Z)
• LLM-as-Judge for Semantic Judging of Powerline Segmentation in UAV Inspection [8.949920712232585]
  We study the feasibility of using a large language model (LLM) as a semantic judge to assess the reliability of power line segmentation results produced by drone-mounted models.<n>LLM produces highly consistent categorical judgments under identical conditions while exhibiting appropriate declines in confidence as visual reliability deteriorates.
  arXiv  Detail & Related papers  (2026-04-07T03:16:44Z)
• Gaming the Judge: Unfaithful Chain-of-Thought Can Undermine Agent Evaluation [76.5533899503582]
  Large language models (LLMs) are increasingly used as judges to evaluate agent performance.<n>We show this paradigm implicitly assumes that the agent's chain-of-thought (CoT) reasoning faithfully reflects both its internal reasoning and the underlying environment state.<n>We demonstrate that manipulated reasoning alone can inflate false positive rates of state-of-the-art VLM judges by up to 90% across 800 trajectories spanning diverse web tasks.
  arXiv  Detail & Related papers  (2026-01-21T06:07:43Z)
• When Wording Steers the Evaluation: Framing Bias in LLM judges [23.16746081917015]
  Large language models (LLMs) are known to produce varying responses depending on prompt phrasing.<n>We investigate how deliberate prompt framing skews model judgments across four high-stakes evaluation tasks.<n>Across 14 judges, we observe clear susceptibility to framing, with model families showing distinct tendencies toward agreement or rejection.
  arXiv  Detail & Related papers  (2026-01-20T02:48:10Z)
• Evaluating and Mitigating LLM-as-a-judge Bias in Communication Systems [32.83708359216193]
  Large Language Models (LLMs) are increasingly being used to autonomously evaluate the quality of content in communication systems.<n>This paper systematically investigates judgment biases in two LLM-as-a-judge models under the point-wise scoring setting.<n>We propose four potential mitigation strategies to ensure fair and reliable AI judging in practical communication scenarios.
  arXiv  Detail & Related papers  (2025-10-14T12:52:29Z)
• 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)
• Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review [36.05498398665352]
  We propose an aspect-guided, multi-level perturbation framework to evaluate the robustness of Large Language Models (LLMs) in automated peer review.<n>Our framework explores perturbations in three key components of the peer review process-papers, reviews, and rebuttals-across several quality aspects.
  arXiv  Detail & Related papers  (2025-02-18T03:50:06Z)

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.