When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models

• URL: http://arxiv.org/abs/2508.10552v1
• Date: Thu, 14 Aug 2025 11:44:52 GMT
• Title: When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models
• Abstract summary: We conduct the first systematic investigation of text dominance across diverse data modalities, including images, videos, audio, time-series, and graphs.<n>Our in-depth analysis identifies three underlying causes: attention dilution from severe token redundancy in non-textual modalities, the influence of fusion architecture design, and task formulations that implicitly favor textual inputs.
• Score: 10.106066580331584
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across a diverse range of multimodal tasks. However, these models suffer from a core problem known as text dominance: they depend heavily on text for their inference, while underutilizing other modalities. While prior work has acknowledged this phenomenon in vision-language tasks, often attributing it to data biases or model architectures. In this paper, we conduct the first systematic investigation of text dominance across diverse data modalities, including images, videos, audio, time-series, and graphs. To measure this imbalance, we propose two evaluation metrics: the Modality Dominance Index (MDI) and the Attention Efficiency Index (AEI). Our comprehensive analysis reveals that text dominance is both significant and pervasive across all tested modalities. Our in-depth analysis identifies three underlying causes: attention dilution from severe token redundancy in non-textual modalities, the influence of fusion architecture design, and task formulations that implicitly favor textual inputs. Furthermore, we propose a simple token compression method that effectively rebalances model attention. Applying this method to LLaVA-7B, for instance, drastically reduces its MDI from 10.23 to a well-balanced value of 0.86. Our analysis and methodological framework offer a foundation for the development of more equitable and comprehensive multimodal language models.

Related papers

• Team RAS in 11th ABAW Competition: Multimodal Ambivalence Recognition Approach [52.92973028971813]
  We present a single text-centered multimodal approach for video-level ambivalence and hesitancy recognition.<n>The proposed approach combines linguistic, acoustic, facial, and scene features using text-centered multimodal fusion model.<n>Experiments on the Behavioural Ambivalence/Hesitancy (BAH) corpus confirm that text is the strongest unimodal modality.
  arXiv  Detail & Related papers  (2026-07-16T08:04:23Z)
• Explicit Representation Alignment for Multimodal Sentiment Analysis [17.25685888421759]
  Multimodal affective analysis aims to understand human sentiment and emotion by jointly modeling heterogeneous modalities such as text and images.<n>We identify representation misalignment between independently pretrained modality encoders as a key bottleneck for effective multimodal learning.<n>We propose a unified multimodal affective analysis framework that leverages vision-language models (VLMs) to convert visual content into structured textual descriptions.
  arXiv  Detail & Related papers  (2026-06-08T07:43:52Z)
• Beyond Language Modeling: An Exploration of Multimodal Pretraining [125.34714978184638]
  We provide empirical clarity through controlled, from-scratch pretraining experiments.<n>We adopt the Transfusion framework, using next-token prediction for language and diffusion for vision.<n>We demonstrate that the MoE architecture harmonizes this scaling asymmetry by providing the high model capacity required by language.
  arXiv  Detail & Related papers  (2026-03-03T18:58:00Z)
• PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models [43.767942065379366]
  Sycophancy is a tendency of AI models to agree with user input at the expense of factual accuracy or in contradiction of visual evidence.<n>We introduce a comprehensive evaluation benchmark, textitPENDULUM, comprising approximately 2,000 human-curated Visual Question Answering pairs.<n>We observe substantial variability in model robustness and a pronounced susceptibility to sycophantic and hallucinatory behavior.
  arXiv  Detail & Related papers  (2025-12-22T12:49:12Z)
• Beyond Spurious Signals: Debiasing Multimodal Large Language Models via Counterfactual Inference and Adaptive Expert Routing [10.66971486730557]
  Multimodal Large Language Models (MLLMs) have shown substantial capabilities in integrating visual and textual information, yet frequently rely on spurious correlations.<n>This paper addresses the critical challenge of superficial correlation bias in MLLMs through a novel causal mediation-based debiasing framework.
  arXiv  Detail & Related papers  (2025-09-18T19:01:11Z)
• MLLMs are Deeply Affected by Modality Bias [158.64371871084478]
  Recent advances in Multimodal Large Language Models (MLLMs) have shown promising results in integrating diverse modalities such as texts and images.<n>MLLMs are heavily influenced by modality bias, often relying on language while under-utilizing other modalities like visual inputs.<n>This paper argues that MLLMs are deeply affected by modality bias, highlighting its manifestations across various tasks.
  arXiv  Detail & Related papers  (2025-05-24T11:49:31Z)
• VOILA: Evaluation of MLLMs For Perceptual Understanding and Analogical Reasoning [63.0285363282581]
  Multimodal Large Language Models (MLLMs) have become a powerful tool for integrating visual and textual information.<n>We introduce VOILA, a benchmark designed to evaluate MLLMs' perceptual understanding and abstract relational reasoning.<n>We reveal that current MLLMs struggle to comprehend inter-image relationships and exhibit limited capabilities in high-level relational reasoning.
  arXiv  Detail & Related papers  (2025-02-25T23:36:19Z)
• A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models [74.48084001058672]
  The rise of foundation models has transformed machine learning research.<n> multimodal foundation models (MMFMs) pose unique interpretability challenges beyond unimodal frameworks.<n>This survey explores two key aspects: (1) the adaptation of LLM interpretability methods to multimodal models and (2) understanding the mechanistic differences between unimodal language models and crossmodal systems.
  arXiv  Detail & Related papers  (2025-02-22T20:55:26Z)
• Cross-Modal Consistency in Multimodal Large Language Models [33.229271701817616]
  We introduce a novel concept termed cross-modal consistency. Our experimental findings reveal a pronounced inconsistency between the vision and language modalities within GPT-4V. Our research yields insights into the appropriate utilization of such models and hints at potential avenues for enhancing their design.
  arXiv  Detail & Related papers  (2024-11-14T08:22:42Z)
• TCAN: Text-oriented Cross Attention Network for Multimodal Sentiment Analysis [26.867610944625337]
  Multimodal Sentiment Analysis (MSA) endeavors to understand human sentiment by leveraging language, visual, and acoustic modalities.<n>Past research predominantly focused on improving representation learning techniques and feature fusion strategies.<n>We introduce a Text-oriented Cross-Attention Network (TCAN) emphasizing the predominant role of the text modality in MSA.
  arXiv  Detail & Related papers  (2024-04-06T07:56:09Z)
• WisdoM: Improving Multimodal Sentiment Analysis by Fusing Contextual World Knowledge [73.76722241704488]
  We propose a plug-in framework named WisdoM to leverage the contextual world knowledge induced from the large vision-language models (LVLMs) for enhanced multimodal sentiment analysis. We show that our approach has substantial improvements over several state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-12T16:08:07Z)
• OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models [122.27878464009181]
  We conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available.
  arXiv  Detail & Related papers  (2023-05-13T11:28:37Z)
• 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)
• MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis [48.776247141839875]
  We propose a novel framework, MISA, which projects each modality to two distinct subspaces. The first subspace is modality-invariant, where the representations across modalities learn their commonalities and reduce the modality gap. Our experiments on popular sentiment analysis benchmarks, MOSI and MOSEI, demonstrate significant gains over state-of-the-art models.
  arXiv  Detail & Related papers  (2020-05-07T15:13:23Z)

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.