Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2505.19616v2
• Date: Thu, 07 Aug 2025 07:46:07 GMT
• Title: Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
• Authors: Rui Cai, Bangzheng Li, Xiaofei Wen, Muhao Chen, Zhe Zhao,
• Abstract summary: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across tasks.<n>They often exhibit difficulty in distinguishing task-relevant from irrelevant signals, particularly in tasks like Visual Question Answering (VQA)<n>This vulnerability becomes more evident in modality-specific tasks such as image classification or pure text question answering.<n>We propose a novel framework to fine-tune MLLMs, including perturbation-based data augmentation with both perturbations and adversarial perturbations.
• Score: 28.20124264650572
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across tasks, yet they often exhibit difficulty in distinguishing task-relevant from irrelevant signals, particularly in tasks like Visual Question Answering (VQA), which can lead to susceptibility to misleading or spurious inputs. We refer to this broader limitation as the Cross-Modality Competency Problem: the model's inability to fairly evaluate all modalities. This vulnerability becomes more evident in modality-specific tasks such as image classification or pure text question answering, where models are expected to rely solely on one modality. In such tasks, spurious information from irrelevant modalities often leads to significant performance degradation. We refer to this failure as Modality Interference, which serves as a concrete and measurable instance of the cross-modality competency problem. We further design a perturbation-based causal diagnostic experiment to verify and quantify this problem. To mitigate modality interference, we propose a novel framework to fine-tune MLLMs, including perturbation-based data augmentations with both heuristic perturbations and adversarial perturbations via Projected Gradient Descent (PGD), and a consistency regularization strategy applied to model outputs with original and perturbed inputs. Experiments on multiple benchmark datasets (image-heavy, text-heavy, and VQA tasks) and multiple model families with different scales demonstrate significant improvements in robustness and cross-modality competency, indicating our method's effectiveness in boosting unimodal reasoning ability while enhancing performance on multimodal tasks.

Related papers

• Learning to Fuse: Modality-Aware Adaptive Scheduling for Robust Multimodal Foundation Models [0.0]
  Modality-Aware Adaptive Fusion Scheduling (MA-AFS) learns to dynamically modulate the contribution of each modality on a per-instance basis.<n>Our work highlights the importance of adaptive fusion and opens a promising direction toward reliable and uncertainty-aware multimodal learning.
  arXiv  Detail & Related papers  (2025-06-15T05:57:45Z)
• 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)
• The Multimodal Paradox: How Added and Missing Modalities Shape Bias and Performance in Multimodal AI [0.0]
  Multimodal learning has proven superior to unimodal counterparts in high-stakes decision-making.<n>While performance gains remain the gold standard for evaluating multimodal systems, concerns around bias and robustness are frequently overlooked.
  arXiv  Detail & Related papers  (2025-05-05T20:42:44Z)
• PAL: Prompting Analytic Learning with Missing Modality for Multi-Modal Class-Incremental Learning [42.00851701431368]
  Multi-modal class-incremental learning (MMCIL) seeks to leverage multi-modal data, such as audio-visual and image-text pairs.<n>A critical challenge remains: the issue of missing modalities during incremental learning phases.<n>We propose PAL, a novel exemplar-free framework tailored to MMCIL under missing-modality scenarios.
  arXiv  Detail & Related papers  (2025-01-16T08:04:04Z)
• Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks [50.75902473813379]
  This work introduces a comprehensive evaluation framework that systematically examines the role of instructions and inputs in the generalisation abilities of such models. The proposed framework uncovers the resilience of multimodal models to extreme instruction perturbations and their vulnerability to observational changes.
  arXiv  Detail & Related papers  (2024-07-04T14:36:49Z)
• Modality Prompts for Arbitrary Modality Salient Object Detection [57.610000247519196]
  This paper delves into the task of arbitrary modality salient object detection (AM SOD) It aims to detect salient objects from arbitrary modalities, eg RGB images, RGB-D images, and RGB-D-T images. A novel modality-adaptive Transformer (MAT) will be proposed to investigate two fundamental challenges of AM SOD.
  arXiv  Detail & Related papers  (2024-05-06T11:02:02Z)
• Spurious Feature Eraser: Stabilizing Test-Time Adaptation for Vision-Language Foundation Model [86.9619638550683]
  Vision-language foundation models have exhibited remarkable success across a multitude of downstream tasks due to their scalability on extensive image-text paired data.<n>However, these models display significant limitations when applied to downstream tasks, such as fine-grained image classification, as a result of decision shortcuts''
  arXiv  Detail & Related papers  (2024-03-01T09:01:53Z)
• Exploiting Modality-Specific Features For Multi-Modal Manipulation Detection And Grounding [54.49214267905562]
  We construct a transformer-based framework for multi-modal manipulation detection and grounding tasks. Our framework simultaneously explores modality-specific features while preserving the capability for multi-modal alignment. We propose an implicit manipulation query (IMQ) that adaptively aggregates global contextual cues within each modality.
  arXiv  Detail & Related papers  (2023-09-22T06:55:41Z)
• Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment [38.574204922793626]
  We present a further analysis of visual modality incompleteness, benchmarking latest MMEA models on our proposed dataset MMEA-UMVM. Our research indicates that, in the face of modality incompleteness, models succumb to overfitting the modality noise, and exhibit performance oscillations or declines at high rates of missing modality. We introduce UMAEA, a robust multi-modal entity alignment approach designed to tackle uncertainly missing and ambiguous visual modalities.
  arXiv  Detail & Related papers  (2023-07-30T12:16:49Z)
• Cross-Attention is Not Enough: Incongruity-Aware Dynamic Hierarchical Fusion for Multimodal Affect Recognition [69.32305810128994]
  Incongruity between modalities poses a challenge for multimodal fusion, especially in affect recognition. We propose the Hierarchical Crossmodal Transformer with Dynamic Modality Gating (HCT-DMG), a lightweight incongruity-aware model. HCT-DMG: 1) outperforms previous multimodal models with a reduced size of approximately 0.8M parameters; 2) recognizes hard samples where incongruity makes affect recognition difficult; 3) mitigates the incongruity at the latent level in crossmodal attention.
  arXiv  Detail & Related papers  (2023-05-23T01:24:15Z)
• Exposing and Addressing Cross-Task Inconsistency in Unified Vision-Language Models [80.23791222509644]
  Inconsistent AI models are considered brittle and untrustworthy by human users. We find that state-of-the-art vision-language models suffer from a surprisingly high degree of inconsistent behavior across tasks. We propose a rank correlation-based auxiliary training objective, computed over large automatically created cross-task contrast sets.
  arXiv  Detail & Related papers  (2023-03-28T16:57:12Z)
• Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions [27.983902791798965]
  We develop a model that generates dilution text that maintains relevance and topical coherence with the image and existing text. We find that the performance of task-specific fusion-based multimodal classifiers drops by 23.3% and 22.5%, respectively, in the presence of dilutions generated by our model. Our work aims to highlight and encourage further research on the robustness of deep multimodal models to realistic variations.
  arXiv  Detail & Related papers  (2022-11-04T17:58:02Z)
• Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering [63.87200781247364]
  Correlation Information Bottleneck (CIB) seeks a tradeoff between compression and redundancy in representations. We derive a tight theoretical upper bound for the mutual information between multimodal inputs and representations.
  arXiv  Detail & Related papers  (2022-09-14T22:04:10Z)

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.