Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models

• URL: http://arxiv.org/abs/2605.08145v1
• Date: Sun, 03 May 2026 06:25:45 GMT
• Title: Self-Captioning Multimodal Interaction Tuning: Amplifying Exploitable Redundancies for Robust Vision Language Models
• Abstract summary: Current vision language models face hallucination and robustness issues against corrupted modalities.<n>We analyze multimodal interactions to determine their impacts on model reliability.<n>Our findings suggest that increasing redundancy can reduce visual induced errors by 38.3% and improve consistency by 16.8%.
• Score: 29.452590895470834
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current vision language models face hallucination and robustness issues against ambiguous or corrupted modalities. We hypothesize that these issues can be addressed by exploiting the shared information between modalities to compensate for the impaired one. To this end, we analyze multimodal interactions -- redundant (shared), unique (exclusive), and synergistic (emergent) task-relevant information provided by the modalities -- to determine their impacts on model reliability. Specifically, amplifying redundant interactions would increase this exploitable shared information to resolve these issues; yet, modern instruction datasets often eliminate redundancies to prioritize visual grounding. We bridge this gap through a self-captioning workflow featuring a \textsc{Multimodal Interaction Gate}: a mechanism to convert unique interactions into redundant interactions. Our findings suggest that increasing redundancy can reduce visual induced errors by 38.3\% and improve consistency by 16.8\%.

Related papers

• Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representations [4.67724003380452]
  Multimodal learning seeks to integrate information from heterogeneous sources, where signals may be shared across modalities, specific to individual modalities, or emerge only through their interaction.<n>While self-supervised multimodal contrastive learning has achieved remarkable progress, most existing methods predominantly capture redundant cross-modal signals, often neglecting modality-specific (unique) and interaction-driven (synergistic) information.<n>Recent extensions broaden this perspective, yet they either fail to explicitly model synergistic interactions or learn different information components in an entangled manner, leading to incomplete representations and potential information leakage.<n>We introduce textbfCOrAL, a principled framework
  arXiv  Detail & Related papers  (2026-02-16T18:06:53Z)
• Plug-and-Play Clarifier: A Zero-Shot Multimodal Framework for Egocentric Intent Disambiguation [60.63465682731118]
  The performance of egocentric AI agents is fundamentally limited by multimodal intent ambiguity.<n>We introduce the Plug-and-Play Clarifier, a zero-shot and modular framework that decomposes the problem into discrete, solvable sub-tasks.<n>Our framework improves the intent clarification performance of small language models by approximately 30%, making them competitive with significantly larger counterparts.
  arXiv  Detail & Related papers  (2025-11-12T04:28:14Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Disentangling Bias by Modeling Intra- and Inter-modal Causal Attention for Multimodal Sentiment Analysis [25.791796193062012]
  Multimodal sentiment analysis (MSA) aims to understand human emotions by integrating information from multiple modalities, such as text, audio, and visual data.<n>Existing methods often suffer from spurious correlations both within and across modalities, leading models to rely on statistical shortcuts rather than true causal relationships.<n>We propose a Multi-relational Multimodal Causal Intervention (MMCI) model, which leverages the backdoor adjustment from causal theory to address the confounding effects of such shortcuts.
  arXiv  Detail & Related papers  (2025-08-07T03:24:04Z)
• Rethinking Explainability in the Era of Multimodal AI [9.57008593971486]
  multimodal AI systems have become ubiquitous and achieved remarkable performance across high-stakes applications.<n>Most existing explainability techniques remain unimodal, generating modality-specific feature attributions, concepts, or circuit traces in isolation.<n>This paper argues that such unimodal explanations systematically misrepresent and fail to capture the cross-modal influence that drives multimodal model decisions.
  arXiv  Detail & Related papers  (2025-06-16T03:08:29Z)
• Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models [26.005367102695317]
  Multimodal Large Language Models can exhibit difficulty in distinguishing task-relevant from irrelevant signals.<n>We show that spurious information from irrelevant modalities often leads to significant performance degradation.<n>We propose a novel framework to finetune MLLMs, including perturbation-based data augmentation with both perturbations and adversarial perturbations.
  arXiv  Detail & Related papers  (2025-05-26T07:31:32Z)
• DeepInteraction++: Multi-Modality Interaction for Autonomous Driving [80.8837864849534]
  We introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout.<n>DeepInteraction++ is a multi-modal interaction framework characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder.<n>Experiments demonstrate the superior performance of the proposed framework on both 3D object detection and end-to-end autonomous driving tasks.
  arXiv  Detail & Related papers  (2024-08-09T14:04:21Z)
• MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts [92.76662894585809]
  We introduce an approach to enhance multimodal models, which we call Multimodal Mixtures of Experts (MMoE) MMoE is able to be applied to various types of models to gain improvement.
  arXiv  Detail & Related papers  (2023-11-16T05:31:21Z)
• Multi-Grained Multimodal Interaction Network for Entity Linking [65.30260033700338]
  Multimodal entity linking task aims at resolving ambiguous mentions to a multimodal knowledge graph. We propose a novel Multi-GraIned Multimodal InteraCtion Network $textbf(MIMIC)$ framework for solving the MEL task.
  arXiv  Detail & Related papers  (2023-07-19T02:11:19Z)
• Switch-BERT: Learning to Model Multimodal Interactions by Switching Attention and Input [27.102030262319197]
  We present textbfSwitch-BERT for joint vision and language representation learning to address the problem of modality mismatch. Switch-BERT extends BERT architecture by introducing learnable layer-wise and cross-layer interactions. Results confirm that, whereas alternative architectures including ViLBERT and UNITER may excel in particular tasks, Switch-BERT can consistently achieve better or comparable performances.
  arXiv  Detail & Related papers  (2023-06-25T09:28:40Z)
• Learning Unseen Modality Interaction [54.23533023883659]
  Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. We pose the problem of unseen modality interaction and introduce a first solution. It exploits a module that projects the multidimensional features of different modalities into a common space with rich information preserved.
  arXiv  Detail & Related papers  (2023-06-22T10:53:10Z)
• 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.