Multimodal Large Language Models as Image Classifiers

• URL: http://arxiv.org/abs/2603.06578v2
• Date: Mon, 09 Mar 2026 12:45:56 GMT
• Title: Multimodal Large Language Models as Image Classifiers
• Abstract summary: Multimodal Large Language Models (MLLM) classification performance depends critically on evaluation protocol and ground truth quality.<n>We identify and fix key issues: model outputs that fall outside the provided class list are discarded, inflated results from weak multiple-choice distractors, and an open-world setting that underperforms only due to poor output mapping.<n>We show that MLLMs can assist human annotators: in a controlled case study, annotators confirmed or integrated MLLMs predictions in approximately 50% of difficult cases.
• Score: 14.022566577479322
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Large Language Models (MLLM) classification performance depends critically on evaluation protocol and ground truth quality. Studies comparing MLLMs with supervised and vision-language models report conflicting conclusions, and we show these conflicts stem from protocols that either inflate or underestimate performance. Across the most common evaluation protocols, we identify and fix key issues: model outputs that fall outside the provided class list and are discarded, inflated results from weak multiple-choice distractors, and an open-world setting that underperforms only due to poor output mapping. We additionally quantify the impact of commonly overlooked design choices - batch size, image ordering, and text encoder selection - showing they substantially affect accuracy. Evaluating on ReGT, our multilabel reannotation of 625 ImageNet-1k classes, reveals that MLLMs benefit most from corrected labels (up to +10.8%), substantially narrowing the perceived gap with supervised models. Much of the reported MLLMs underperformance on classification is thus an artifact of noisy ground truth and flawed evaluation protocol rather than genuine model deficiency. Models less reliant on supervised training signals prove most sensitive to annotation quality. Finally, we show that MLLMs can assist human annotators: in a controlled case study, annotators confirmed or integrated MLLMs predictions in approximately 50% of difficult cases, demonstrating their potential for large-scale dataset curation. This work is part of the Aiming for Perfect ImageNet-1k project, see https://klarajanouskova.github.io/ImageNet/.

Related papers

• Learning to Trust the Crowd: A Multi-Model Consensus Reasoning Engine for Large Language Models [0.0]
  Large language models (LLMs) achieve strong aver- age performance yet remain unreliable at the instance level.<n>We introduce a Multi-Model Consensus Reasoning Engine that treats the set of LLM outputs as input to a supervised meta-learner.<n>The system maps natural language responses into structured features using semantic embeddings, pairwise similarity and clustering statistics, lexical and structural cues, reasoning-quality scores, confidence estimates, and model-specific priors.
  arXiv  Detail & Related papers  (2026-01-12T06:27:06Z)
• When Scale Meets Diversity: Evaluating Language Models on Fine-Grained Multilingual Claim Verification [14.187153195380668]
  Large language models have remarkable capabilities across many NLP tasks, but their effectiveness for multilingual claim verification with nuanced classification schemes remains understudied.<n>We evaluate five state-of-the-art language models on the X-Fact dataset, which spans 25 languages with seven distinct veracity categories.<n>Surprisingly, we find that XLM-R substantially outperforms all tested LLMs, achieving 57.7% macro-F1 compared to the best LLM performance of 16.9%.
  arXiv  Detail & Related papers  (2025-07-28T10:49:04Z)
• Can Reasoning Help Large Language Models Capture Human Annotator Disagreement? [84.32752330104775]
  Variation in human annotation (i.e., disagreements) is common in NLP.<n>We evaluate the influence of different reasoning settings on Large Language Model disagreement modeling.<n>Surprisingly, our results show that RLVR-style reasoning degrades performance in disagreement modeling.
  arXiv  Detail & Related papers  (2025-06-24T09:49:26Z)
• Demystifying the Visual Quality Paradox in Multimodal Large Language Models [49.154146792279946]
  Recent Multimodal Large Language Models (MLLMs) excel on benchmark vision-language tasks, yet little is known about how input visual quality shapes their responses.<n>We conduct the first systematic study spanning leading MLLMs and a suite of vision-language benchmarks.<n>We uncover a visual-quality paradox: model, task, and even individual-instance performance can improve when images deviate from human-perceived fidelity.
  arXiv  Detail & Related papers  (2025-06-18T17:14:07Z)
• Reasoning Multimodal Large Language Model: Data Contamination and Dynamic Evaluation [9.434966074326056]
  Multimodal Large Language Models (MLLMs) show impressive vision-language benchmark performance, yet growing concerns about data contamination risk masking true generalization.<n>We propose a novel dynamic evaluation framework to rigorously assess MLLM generalization, moving beyond static benchmarks.<n>We demonstrate that fine-tuning on simulated test data (extreme contamination) drastically sharpens task-specific performance but harms overall generalization.
  arXiv  Detail & Related papers  (2025-06-08T15:52:38Z)
• Grounded Chain-of-Thought for Multimodal Large Language Models [66.04061083611863]
  We propose a new learning task for multimodal large language models (MLLMs) called Grounded Chain-of-Thought (GCoT)<n>GCoT is keen to helping MLLMs to recognize and ground the relevant visual cues step by step, thereby predicting the correct answer with grounding coordinates as the intuitive basis.<n>To facilitate this task, we also carefully design and construct a dataset called multimodal grounded chain-of-thought (MM-GCoT) consisting of 24,022 GCoT examples for 5,033 images.
  arXiv  Detail & Related papers  (2025-03-17T04:07:47Z)
• SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models [74.40683913645731]
  Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications.<n>Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth.<n>Analysis of these prompt scores reveals VLM biases and AND''/OR' signal ambiguities, notably that maximum scores are surprisingly suboptimal compared to second-highest scores.
  arXiv  Detail & Related papers  (2025-02-24T07:15:05Z)
• Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model Performance [28.524573212179124]
  Large language models (LLMs) offer new opportunities to enhance the annotation process.<n>We compare expert, crowd-sourced, and LLM-based annotations in terms of the agreement, label quality, and efficiency.<n>Our findings reveal a substantial number of label errors, which, when corrected, a significant upward shift in reported model performance.
  arXiv  Detail & Related papers  (2024-10-24T16:27:03Z)
• VHELM: A Holistic Evaluation of Vision Language Models [75.88987277686914]
  We present the Holistic Evaluation of Vision Language Models (VHELM) VHELM aggregates various datasets to cover one or more of the 9 aspects: visual perception, knowledge, reasoning, bias, fairness, multilinguality, robustness, toxicity, and safety. Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast.
  arXiv  Detail & Related papers  (2024-10-09T17:46:34Z)
• MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMs [38.93090238335506]
  Spurious bias, a tendency to use spurious correlations between non-essential input attributes and target variables for predictions, has revealed a severe pitfall in deep learning models trained on single modality data. We introduce MM-SpuBench, a comprehensive visual question-answering (VQA) benchmark designed to evaluate MLLMs' reliance on nine distinct categories of spurious correlations. Our findings illuminate the persistence of the reliance on spurious correlations from these models and underscore the urge for new methodologies to mitigate spurious biases.
  arXiv  Detail & Related papers  (2024-06-24T20:29:16Z)
• Large Language Models are Biased Reinforcement Learners [0.0]
  We show that large language models (LLMs) exhibit behavioral signatures of a relative value bias. Computational cognitive modeling reveals that LLM behavior is well-described by a simple RL algorithm.
  arXiv  Detail & Related papers  (2024-05-19T01:43:52Z)
• Debiasing Multimodal Large Language Models via Penalization of Language Priors [38.97645845493758]
  Multimodal Large Language Models (MLLMs) have become indispensable tools in computer vision and natural language processing.<n>Despite their advancements, our investigation reveals a noteworthy bias: the generated content is often driven more by the inherent priors of the underlying Large Language Models (LLMs) than by the input image.<n>We propose two simple, training-free strategies to rectify these biases and redirect the model's focus toward visual information.
  arXiv  Detail & Related papers  (2024-03-08T12:35:07Z)
• The Instinctive Bias: Spurious Images lead to Illusion in MLLMs [34.91795817316696]
  We identify a typical class of inputs that baffles MLLMs, which consist of images that are highly relevant but inconsistent with answers. We propose CorrelationQA, the first benchmark that assesses the visual illusion level given spurious images. We conduct a thorough analysis on 9 mainstream MLLMs, illustrating that they universally suffer from this instinctive bias to varying degrees.
  arXiv  Detail & Related papers  (2024-02-06T06:48:46Z)
• Machine Vision Therapy: Multimodal Large Language Models Can Enhance Visual Robustness via Denoising In-Context Learning [67.0609518552321]
  We propose to conduct Machine Vision Therapy which aims to rectify the noisy predictions from vision models. By fine-tuning with the denoised labels, the learning model performance can be boosted in an unsupervised manner.
  arXiv  Detail & Related papers  (2023-12-05T07:29:14Z)
• Effective Proxy for Human Labeling: Ensemble Disagreement Scores in Large Language Models for Industrial NLP [6.429005147017301]
  We demonstrate that ensemble disagreement scores work well as a proxy for human labeling for language models in zero-shot, few-shot, and fine-tuned settings. Results across various languages and domains show disagreement scores provide a better estimation of model performance with mean average error (MAE) as low as 0.4% and on average 13.8% better than using silver labels.
  arXiv  Detail & Related papers  (2023-09-11T17:07:01Z)
• The Devil is in the Errors: Leveraging Large Language Models for Fine-grained Machine Translation Evaluation [93.01964988474755]
  AutoMQM is a prompting technique which asks large language models to identify and categorize errors in translations. We study the impact of labeled data through in-context learning and finetuning. We then evaluate AutoMQM with PaLM-2 models, and we find that it improves performance compared to just prompting for scores.
  arXiv  Detail & Related papers  (2023-08-14T17:17:21Z)
• MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models [111.51612340032052]
  Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks.<n>This paper presents the first comprehensive MLLM Evaluation benchmark MME.<n>It measures both perception and cognition abilities on a total of 14 subtasks.
  arXiv  Detail & Related papers  (2023-06-23T09:22:36Z)
• Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models [76.410400238974]
  We propose TTA with feedback to rectify the model output and prevent the model from becoming blindly confident. A CLIP model is adopted as the reward model during TTA and provides feedback for the VLM. The proposed textitreinforcement learning with CLIP feedback(RLCF) framework is highly flexible and universal.
  arXiv  Detail & Related papers  (2023-05-29T11:03:59Z)

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.