MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2607.27637v2
• Date: Sat, 01 Aug 2026 04:59:28 GMT
• Title: MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models
• Abstract summary: A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts.<n>Existing benchmarks mainly target OOC or visually unanswerable questions.<n>We present MMOOC, a large-scale benchmark for evaluating refusal and robust answering abilities of MLLMs.
• Score: 20.709465270147387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or shifted contexts. A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts while still answering shifted in-context (Shifted IC) questions with non-subject context shifts. Existing benchmarks mainly target OOC or visually unanswerable questions, but overlook answerable Shifted IC cases and cover limited OOC shifts. To fill this gap, we present MMOOC, a large-scale benchmark for evaluating refusal and robust answering abilities of MLLMs. MMOOC contains over 41K image-question pairs, including answerable Shifted IC cases and unanswerable OOC cases, spanning three question formats, eight shift types and six visual scenarios, with data quality ensured through MLLM-based filtering and human verification. We evaluate model responses using Accuracy and Refusal Rate, and further introduce an LLM-as-a-Judge metric to assess the correctness of model reasoning. Experiments on diverse MLLMs show that current models still struggle to balance answer-ability and refusal under shifted contexts. We further analyze key failure patterns and show that post-training can improve robustness. MMOOC will be made publicly available.

Related papers

• Large Multimodal Models as General In-Context Classifiers [73.11242790834383]
  In this work, we argue that this answer overlooks an important capability of LMMs: in-context learning.<n>We benchmark state-of-the-art LMMs on diverse datasets for closed-world classification and find that, although their zero-shot performance is lower than CLIP's, LMMs with a few in-context examples can match or even surpass contrastive VLMs with cache-based adapters.<n>We extend this analysis to the open-world setting, where the generative nature of LMMs makes them more suitable for the task.
  arXiv  Detail & Related papers  (2026-02-26T17:08:18Z)
• Q-Doc: Benchmarking Document Image Quality Assessment Capabilities in Multi-modal Large Language Models [19.598563198222035]
  We propose Q-Doc to systematically probing DIQA capabilities of MLLMs at coarse, middle, and fine granularity levels.<n>We show that while MLLMs possess nascent DIQA abilities, they exhibit critical limitations: inconsistent scoring, distortion misidentification, and severity misjudgment.<n>Our work provides a benchmark for DIQA capabilities in MLLMs, revealing pronounced deficiencies in their quality perception and promising pathways for enhancement.
  arXiv  Detail & Related papers  (2025-11-14T15:41:17Z)
• Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models [2.393011821499345]
  We investigate the presence and nature of selection bias in Large Vision-Language Models (LVLMs)<n>We propose an inference-time logit-level debiasing method that estimates an ensemble bias vector from general and contextual prompts.<n>Our method mitigates bias without retraining and is compatible with frozen LVLMs.
  arXiv  Detail & Related papers  (2025-09-20T20:45:47Z)
• A Multi-To-One Interview Paradigm for Efficient MLLM Evaluation [63.76972456980632]
  We propose a multi-to-one interview paradigm for efficient MLLM evaluation.<n>Our framework consists of (i) a two-stage interview strategy with pre-interview and formal interview phases, (ii) dynamic adjustment of weights to ensure fairness, and (iii) an adaptive mechanism for question difficulty-level chosen.
  arXiv  Detail & Related papers  (2025-09-18T12:07:40Z)
• 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)
• Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models [45.63440666848143]
  Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities.<n>Despite their success, MLLMs remain vulnerable to conversational adversarial inputs.<n>We study gaslighting negation attacks: a phenomenon where models, despite initially providing correct answers, are persuaded by user-provided negations to reverse their outputs.
  arXiv  Detail & Related papers  (2025-01-31T10:37:48Z)
• EmbodiedEval: Evaluate Multimodal LLMs as Embodied Agents [57.468696197956604]
  EmbodiedEval is a comprehensive and interactive evaluation benchmark for MLLMs with embodied tasks.<n>It covers a broad spectrum of existing embodied AI tasks with significantly enhanced diversity.<n>We evaluated the state-of-the-art MLLMs on EmbodiedEval and found that they have a significant shortfall compared to human level on embodied tasks.
  arXiv  Detail & Related papers  (2025-01-21T03:22:10Z)
• 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)
• Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning [77.72128397088409]
  We show that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question.<n>We also propose a novel reinforcement learning paradigm to encourage the model to actively perform composite deduction.
  arXiv  Detail & Related papers  (2024-04-19T15:53:27Z)
• LLMs May Perform MCQA by Selecting the Least Incorrect Option [29.202758753639078]
  Large Language Models (LLMs) have markedly enhanced performance across a variety of tasks.<n>The adoption of Multiple Choice Question Answering (MCQA) as a benchmark for assessing LLMs has gained considerable traction.<n>However, concerns regarding the robustness of this evaluative method persist.
  arXiv  Detail & Related papers  (2024-02-02T12:07:00Z)
• MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria [49.500322937449326]
  Multimodal large language models (MLLMs) have broadened the scope of AI applications. Existing automatic evaluation methodologies for MLLMs are mainly limited in evaluating queries without considering user experiences. We propose a new evaluation paradigm for MLLMs, which is evaluating MLLMs with per-sample criteria using potent MLLM as the judge.
  arXiv  Detail & Related papers  (2023-11-23T12:04:25Z)
• Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task [18.623619585980688]
  We propose a unified robustness evaluation framework based on the slot-filling task to evaluate the dialogue understanding capability of large language models. Specifically, we construct a input perturbation evaluation dataset, Noise-LLM, which contains five types of single perturbation and four types of mixed perturbation data. Our aim is to assess how well various robustness methods of LLMs perform in real-world noisy scenarios.
  arXiv  Detail & Related papers  (2023-10-10T10:22:05Z)
• Simultaneous Machine Translation with Large Language Models [51.470478122113356]
  We investigate the possibility of applying Large Language Models to SimulMT tasks. We conducted experiments using the textttLlama2-7b-chat model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics.
  arXiv  Detail & Related papers  (2023-09-13T04:06:47Z)

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.