Source-Modality Monitoring in Vision-Language Models

• URL: http://arxiv.org/abs/2604.22038v1
• Date: Thu, 23 Apr 2026 19:49:36 GMT
• Title: Source-Modality Monitoring in Vision-Language Models
• Abstract summary: We consider source-modality monitoring as an instance of the more general binding problem.<n>We find that both syntactic and semantic signals play an important role, but that the latter tend to outweigh the former in cases when modalities are highly distinct distributionally.
• Score: 16.990140746029553
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We define and investigate source-modality monitoring -- the ability of multimodal models to track and communicate the input source from which pieces of information originate. We consider source-modality monitoring as an instance of the more general binding problem, and evaluate the extent to which models exploit syntactic vs. semantic signals in order to bind words like image in a user-provided prompt to specific components of their input and context (i.e., actual images). Across experiments spanning 11 vision-language models (VLMs) performing target-modality information retrieval tasks, we find that both syntactic and semantic signals play an important role, but that the latter tend to outweigh the former in cases when modalities are highly distinct distributionally. We discuss the implications of these findings for model robustness, and in the context of increasingly multimodal agentic systems.

Related papers

• Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition [13.945344883914318]
  We introduce Partial Information Decomposition (PID) as a decision-level framework that separates unique, redundant, and synergistic contributions of sensory and linguistic inputs.<n>We extend PID to tri-modal systems with Sensory PID, treating language as a control variable to decompose video--audio information gain.
  arXiv  Detail & Related papers  (2026-05-31T02:29:36Z)
• Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval [60.25608870901428]
  Trustworthiness is a core research challenge for agentic AI systems built on Large Language Models (LLMs)<n>We propose the task of fact-checking without retrieval, focusing on the verification of arbitrary natural language claims, independent of their source robustness.
  arXiv  Detail & Related papers  (2026-03-05T18:42:51Z)
• DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories [52.57197752244638]
  We introduce DeepImageSearch, a novel agentic paradigm that reformulates image retrieval as an autonomous exploration task.<n>Models must plan and perform multi-step reasoning over raw visual histories to locate targets based on implicit contextual cues.<n>We construct DISBench, a challenging benchmark built on interconnected visual data.
  arXiv  Detail & Related papers  (2026-02-11T12:51:10Z)
• Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional [40.11148315577635]
  We present a large-scale empirical study to quantify dependencies across 23 visual question-answering benchmarks using multi-modal large language models (MLLMs)<n>Our findings show that the reliance on vision, question (text), and their interaction varies significantly, both across and within benchmarks.<n>We discover that numerous benchmarks intended to mitigate text-only biases have inadvertently amplified image-only dependencies.<n>This characterization persists across model sizes, as larger models often use these intra-modality dependencies to achieve high performance that mask an underlying lack of multi-modal reasoning.
  arXiv  Detail & Related papers  (2025-09-27T21:13:29Z)
• How Do Vision-Language Models Process Conflicting Information Across Modalities? [15.90185747024602]
  This paper seeks to understand how such models behave when input streams present conflicting information.<n>We find that models often favor one modality over the other, e.g., reporting the image regardless of what the caption says, but that different models differ in which modality they favor.
  arXiv  Detail & Related papers  (2025-07-02T15:15:14Z)
• Multi-Faceted Multimodal Monosemanticity [42.64636740703632]
  We take a data-driven approach to analyze interpretable, monosemantic features extracted from deep multimodal models.<n>Specifically, we investigate CLIP, a prominent visual-language representation model trained on massive image-text pairs.<n>We develop a set of multi-modal interpretability tools and measures designed to disentangle and analyze features learned from CLIP.
  arXiv  Detail & Related papers  (2025-02-16T14:51:07Z)
• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• 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)
• Unified Discrete Diffusion for Simultaneous Vision-Language Generation [78.21352271140472]
  We present a unified multimodal generation model that can conduct both the "modality translation" and "multi-modality generation" tasks. Specifically, we unify the discrete diffusion process for multimodal signals by proposing a unified transition matrix. Our proposed method can perform comparably to the state-of-the-art solutions in various generation tasks.
  arXiv  Detail & Related papers  (2022-11-27T14:46:01Z)
• 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)
• High-Modality Multimodal Transformer: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning [112.51498431119616]
  This paper studies efficient representation learning for high-modality scenarios involving a large set of diverse modalities. A single model, HighMMT, scales up to 10 modalities (text, image, audio, video, sensors, proprioception, speech, time-series, sets, and tables) and 15 tasks from 5 research areas.
  arXiv  Detail & Related papers  (2022-03-02T18:56:20Z)

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.