Multimodal Model Interpretability

Ask about this topic

Overview

It asks which modalities, regions, tokens, concepts, or internal circuits support a model’s output, helping people audit errors, shortcuts, bias, and safety. Common approaches include saliency and Shapley attribution, concept bottlenecks and sparse autoencoders, and probing or causal interventions that test what happens when evidence is altered. Researchers evaluate these explanations on visual question answering, hallucination and grounding tasks, cross-modal benchmarks, and clinical settings where inputs may be missing or incomplete. A central tension is that an explanation can look plausible without being faithful: models may encode useful evidence yet ignore it, favor one modality, or rely on shortcuts, and evaluation of genuine cross-modal reasoning remains difficult.

Latest papers

CardsList

130 papers13 papers in the last four weeks, down 7% on the four weeks before. 0.1% of all new papers.

  1. Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models

    Apr 18, 2026Xinru Yan, Boxi Cao, Yaojie Lu +4Unified Multimodal ModelsNeural Network Interpretability

    University of Chinese Academy of Sciences, Beijing, China · Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences, Beijing, China

  2. Real-Time Visual Attribution Streaming in Thinking Model

    Apr 17, 2026Seil Kang, Woojung Han, Junhyeok Kim +3VLM InterpretabilityMultimodal Reasoning

    YYonsei University. · AAmazon.

  3. Dynamic Summary Generation for Interpretable Multimodal Depression Detection

    Apr 13, 2026Shiyu Teng, Jiaqing Liu, Hao Sun +6Depression DetectionDepression Severity Estimation

    College of Information Science and Engineering, Ritsumeikan University, Shiga, Japan · College of Computer Science and Technology, Zhejiang University, Hangzhou, China · Faculty of Engineering, University of the Ryukyus, Japan

  4. Diffusion-CAM: Faithful Visual Explanations for dMLLMs

    Apr 13, 2026Haomin Zuo, Yidi Li, Luoxiao Yang +1Multimodal Model InterpretabilityFeature Attribution

    Sun Yat-sen University · Northwestern University · Technion - Israel Institute of Technology +1

  5. Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models

    Apr 13, 2026Songlin Yang, Xianghao Kong, Anyi RaoUnified Multimodal ModelsMultimodal Generation

  6. Tree-of-Evidence: Efficient "System 2" Search for Faithful Multimodal Grounding

    Apr 9, 2026Micky C. Nnamdi, Benoit L. Marteau, Yishan Zhong +2Multimodal Model InterpretabilityMultimodal Grounding

    Georgia Institute of Technology

  7. Beyond Semantics: Disentangling Information Scope in Sparse Autoencoders for CLIP

    Apr 7, 2026Yusung Ro, Jaehyun Choi, Junmo KimNeural Network InterpretabilityVLM Interpretability

    KAIST · Korea AI Safety Institute, ETRI

  8. Scalable and Explainable Learner-Video Interaction Prediction using Multimodal Large Language Models

    Apr 6, 2026Dominik Glandorf, Fares Fawzi, Tanja KäserVideo UnderstandingMultimodal Model Interpretability

    EPFL, Switzerland

  9. MultiPress: A Multi-Agent Framework for Interpretable Multimodal News Classification

    Apr 4, 2026Tailong Luo, Hao Li, Rong Fu +7Multimodal ClassificationMultimodal Agents

    New York Institute of Technology · University of Arizona · University of Macau +3

  10. Do Audio-Visual Large Language Models Really See and Hear?

    Apr 3, 2026Ramaneswaran Selvakumar, Kaousheik Jayakumar, S Sakshi +3Multimodal Large Language ModelsAudio-Visual Understanding

    University of Maryland, College Park

  11. Quantifying Cross-Modal Interactions in Multimodal Glioma Survival Prediction via InterSHAP: Evidence for Additive Signal Integration

    Mar 31, 2026Iain Swift, JingHua Ye, Ruairi O'ReillyMultimodal FusionMultimodal Survival Analysis

    Department of Computer Science, Munster Technological University, Cork, Ireland

  12. Structural Graph Probing of Vision-Language Models

    Mar 28, 2026Haoyu He, Yue Zhuo, Yu Zheng +1VLM InterpretabilityMultimodal Model Interpretability

    Northeastern University · Massachusetts Institute of Technology

  13. Probabilistic Concept Graph Reasoning for Multimodal Misinformation Detection

    Mar 26, 2026Ruichao Yang, Wei Gao, Xiaobin Zhu +5Graph ReasoningMultimodal Robustness

    University of Science and Technology Beijing · Singapore Management University · Hong Kong Baptist University

  14. A Neuro-Symbolic System for Interpretable Multimodal Physiological Signals Integration in Human Fatigue Detection

    Mar 25, 2026Mohammadreza Jamalifard, Yaxiong Lei, Parasto Azizinezhad +2Multimodal Model InterpretabilityNeuro-Symbolic Reasoning

    School of Computer Science and Electronic Engineering, University of Essex, United Kingdom

  15. From Prediction to Diagnosis: Reasoning-Aware AI for Photovoltaic Defect Inspection

    Mar 24, 2026Dev Mistry, Feng Qiu, Bo Chen +4Fault DetectionIndustrial Inspection

    Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL 60616, USA · Argonne National Laboratory, Lemont, IL 60439, USA · Smart Grid Emerging Technology Department, Commonwealth Edison, Chicago, IL 60618, USA +2

  16. OmniTrace: A Unified Framework for Generation-Time Source Attribution in Omni-Modal LLMs

    Mar 20, 2026Qianqi Yan, Yichen Guo, Ching-Chen Kuo +4Multimodal Model InterpretabilityMultimodal Large Language Models

    University of California, Santa Barbara · eBay

  17. DCG-Net: Dual Cross-Attention with Concept-Value Graph Reasoning for Interpretable Medical Diagnosis

    Mar 20, 2026Getamesay Dagnaw, Xuefei Yin, Muhammad Hassan Maqsood +2Explainable Medical Image AnalysisMedical Image Classification

    School of Information and Communication Technology, Griffith University, QLD, Australia

  18. Multimodal Model for Computational Pathology:Representation Learning and Image Compression

    Mar 19, 2026Peihang Wu, Zehong Chen, Lijian XuComputational PathologyWhole-Slide Image Analysis

    Shenzhen University of Advanced Technology

  19. Cross-Modal Rationale Transfer for Explainable Humanitarian Classification on Social Media

    Mar 19, 2026Thi Huyen Nguyen, Koustav Rudra, Wolfgang NejdlClassificationMultimodal Classification

    L3S Research Center, Leibniz University Hannover, Hannover, Germany · Indian Institute of Technology Kharagpur, Kharagpur, India

  20. Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prediction with Multimodal Biomedical Data

    Mar 17, 2026Sophie Kearney, Shu Yang, Zixuan Wen +8Alzheimer's Disease ClassificationTabular Foundation Models

    University of Pennsylvania, Philadelphia, PA, USA · Stony Brook University, Stony Brook, NY, USA · University of North Carolina at Chapel Hill, Chapel Hill, NC, USA +2

  21. SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis

    Mar 14, 2026Ehud Gordon, Meir Yossef Levi, Guy GilboaCanonical Correlation AnalysisMultimodal Model Interpretability

    Viterbi Faculty of Electrical and Computer Engineering, Technion – Israel Institute of Technology, Haifa, Israel

  22. Towards Faithful Multimodal Concept Bottleneck Models

    Mar 13, 2026Pierre Moreau, Emeline Pineau Ferrand, Yann Choho +3Concept Bottleneck ModelsMultimodal Model Interpretability

    Ekimetrics, F-75009 Paris, France · Télécom Paris, F-91120 Palaiseau, France · Sorbonne Université, CNRS, LIP6, F-75005 Paris, France

  23. Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition

    Mar 12, 2026Umberto Cappellazzo, Stavros Petridis, Maja PanticAudio-Visual Speech RecognitionModality Imbalance

    Imperial College London, UK · NatWest AI Research, UK

  24. FBCIR: Balancing Cross-Modal Focuses in Composed Image Retrieval

    Mar 12, 2026Chenchen Zhao, Jianhuan Zhuo, Muxi Chen +6Modality Reliance in Multimodal ModelsComposed Image Retrieval

    Department of Computer Science and Engineering, The Chinese University of Hong Kong · Tencent AI Data Department · School of Mathematical Sciences, Dalian University of Technology +1

  25. Feature-level Interaction Explanations in Multimodal Transformers

    Mar 4, 2026Yeji Kim, Housam Khalifa Bashier Babiker, Mi-Young Kim +1Multimodal UnderstandingFeature Attribution

    University of Alberta, Edmonton, AB, Canada · University of Waikato, Hamilton, New Zealand · University of Alberta, Camrose, AB, Canada

  26. Bridging the gap between Performance and Interpretability: An Explainable Disentangled Multimodal Framework for Cancer Survival Prediction

    Mar 2, 2026Aniek Eijpe, Soufyan Lakbir, Melis Erdal Cesur +4Cancer Survival PredictionMultimodal Survival Analysis

    AI Technology for Life, Department of Information and Computing Sciences, Department of Biology, Utrecht University, Utrecht, The Netherlands · Department of Metabolic Diseases, Wilhelmina Children’s Hospital, University Medical Center Utrecht, Utrecht, The Netherlands · Regenerative Medicine Center Utrecht, Utrecht, The Netherlands +3

  27. PathMoE: Interpretable Multimodal Interaction Experts for Pediatric Brain Tumor Classification

    Mar 2, 2026Jian Yu, Joakim Nguyen, Jinrui Fang +10Brain Tumor ClassificationMultimodal Classification

    University of Texas, Austin, TX, USA · Dell Children’s Medical Center, Austin, TX, USA · University of North Carolina at Chapel Hill, NC, USA +1

  28. What Do Visual Tokens Really Encode? Uncovering Sparsity and Redundancy in Multimodal Large Language Models

    Feb 28, 2026Yingqi Fan, Junlong Tong, Anhao Zhao +1Multimodal Large Language ModelsMultimodal Model Interpretability

    Institute of Digital Twin, Eastern Institute of Technology, Ningbo · Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative · Shanghai Jiao Tong University +1

  29. A multimodal slice discovery framework for systematic failure detection and explanation in medical image classification

    Feb 27, 2026Yixuan Liu, Kanwal K. Bhatia, Ahmed E. FetitAlgorithmic AuditingMedical Image Classification

    Department of Computing, Imperial College London, UK · Aival, London, UK

  30. AR&D: A Framework for Retrieving and Describing Concepts for Interpreting AudioLLMs

    Feb 24, 2026Townim Faisal Chowdhury, Ta Duc Huy, Siqi Pan +2Multimodal Model InterpretabilityMechanistic Interpretability

    Australian Institute for Machine Learning, University of Adelaide · Dolby Laboratories · School of Computer and Mathematical Sciences, University of Adelaide, Australia