# MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks

arXiv: https://arxiv.org/abs/2212.08158 · HTML: https://mlsanity.com/paper/2212.08158/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 52 references that are in the map.
- First posted on arXiv 15 Dec 2022.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Modeling Context in Referring Expressions](https://mlsanity.com/paper/1608.00272/) (2016)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers](https://mlsanity.com/paper/1604.00825/) (2016)
- [VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://mlsanity.com/paper/2112.07566/) (2021)
- [FOIL it! Find One mismatch between Image and Language caption](https://mlsanity.com/paper/1705.01359/) (2017)
- [Behind the Scene: Revealing the Secrets of Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2005.07310/) (2020)
- [Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers](https://mlsanity.com/paper/2109.04448/) (2021)
- [Does my multimodal model learn cross-modal interactions? It's harder to tell than you might think!](https://mlsanity.com/paper/2010.06572/) (2020)
- [Gender Artifacts in Visual Datasets](https://mlsanity.com/paper/2206.09191/) (2022)
- [Perceptual Score: What Data Modalities Does Your Model Perceive?](https://mlsanity.com/paper/2110.14375/) (2021)
- [Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks](https://mlsanity.com/paper/2012.12352/) (2020)
- [DIME: Fine-grained Interpretations of Multimodal Models via Disentangled Local Explanations](https://mlsanity.com/paper/2203.02013/) (2022)

## Built on by (most cited first, 30 of 43)

- [Quantifying and Mitigating Unimodal Biases in Multimodal Large Language Models: A Causal Perspective](https://mlsanity.com/paper/2403.18346/) (2024)
- [Evaluating and Steering Modality Preferences in Multimodal Large Language Model](https://mlsanity.com/paper/2505.20977/) (2025)
- [Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?](https://mlsanity.com/paper/2404.18624/) (2024)
- [When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs](https://mlsanity.com/paper/2511.02243/) (2025)
- [How and where does CLIP process negation?](https://mlsanity.com/paper/2407.10488/) (2024)
- [Measuring Cross-Modal Interactions in Multimodal Models](https://mlsanity.com/paper/2412.15828/) (2024)
- [Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language Models](https://mlsanity.com/paper/2412.14133/) (2024)
- [SPEX: Scaling Feature Interaction Explanations for LLMs](https://mlsanity.com/paper/2502.13870/) (2025)
- [MultiSHAP: A Shapley-Based Framework for Explaining Cross-Modal Interactions in Multimodal AI Models](https://mlsanity.com/paper/2508.00576/) (2025)
- [Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It](https://mlsanity.com/paper/2507.13328/) (2025)
- [Explaining Similarity in Vision-Language Encoders with Weighted Banzhaf Interactions](https://mlsanity.com/paper/2508.05430/) (2025)
- [Beyond Cross-Modal Alignment: Measuring and Leveraging Modality Gap in Vision-Language Models](https://mlsanity.com/paper/2502.14888/) (2025)
- [VISaGE: Understanding Visual Generics and Exceptions](https://mlsanity.com/paper/2510.12548/) (2025)
- [SurvBeX: An explanation method of the machine learning survival models based on the Beran estimator](https://mlsanity.com/paper/2308.03730/) (2023)
- [Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional](https://mlsanity.com/paper/2509.23499/) (2025)
- [Complementarity-Supervised Spectral-Band Routing for Multimodal Emotion Recognition](https://mlsanity.com/paper/2603.13340/) (2026)
- [Interpreting Vision and Language Generative Models with Semantic Visual Priors](https://mlsanity.com/paper/2304.14986/) (2023)
- [Feasibility of Detecting Cognitive Impairment and Psychological Well-being among Older Adults Using Facial, Acoustic, Linguistic, and Cardiovascular Patterns Derived from Remote Conversations](https://mlsanity.com/paper/2412.14194/) (2024)
- [What are You Looking at? Modality Contribution in Multimodal Medical Deep Learning](https://mlsanity.com/paper/2503.01904/) (2025)
- [On the Risk of Misleading Reports: Diagnosing Textual Biases in Multimodal Clinical AI](https://mlsanity.com/paper/2508.00171/) (2025)
- [Investigating Modality Contribution in Audio LLMs for Music](https://mlsanity.com/paper/2509.20641/) (2025)
- [The Scenario Refiner: Grounding subjects in images at the morphological level](https://mlsanity.com/paper/2309.11252/) (2023)
- [SURE-VQA: Systematic Understanding of Robustness Evaluation in Medical VQA Tasks](https://mlsanity.com/paper/2411.19688/) (2024)
- [Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions](https://mlsanity.com/paper/2502.13034/) (2025)
- [Unveiling Modality Bias: Automated Sample-Specific Analysis for Multimodal Misinformation Benchmarks](https://mlsanity.com/paper/2511.05883/) (2025)
- [Quantifying Modality Contributions via Disentangling Multimodal Representations](https://mlsanity.com/paper/2511.19470/) (2025)
- [Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition](https://mlsanity.com/paper/2603.12046/) (2026)
- [Feature-level Interaction Explanations in Multimodal Transformers](https://mlsanity.com/paper/2603.13326/) (2026)
- [Medical Context Distorts Decisions in Clinical Vision Language Models](https://mlsanity.com/paper/2605.17436/) (2026)
- [Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable Sensors](https://mlsanity.com/paper/2605.17618/) (2026)

## Abstract (arXiv)

Vision and language models (VL) are known to exploit unrobust indicators in individual modalities (e.g., introduced by distributional biases) instead of focusing on relevant information in each modality. That a unimodal model achieves similar accuracy on a VL task to a multimodal one, indicates that so-called unimodal collapse occurred. However, accuracy-based tests fail to detect e.g., when the model prediction is wrong, while the model used relevant information from a modality. Instead, we propose MM-SHAP, a performance-agnostic multimodality score based on Shapley values that reliably quantifies in which proportions a multimodal model uses individual modalities. We apply MM-SHAP in two ways: (1) to compare models for their average degree of multimodality, and (2) to measure for individual models the contribution of individual modalities for different tasks and datasets. Experiments with six VL models -- LXMERT, CLIP and four ALBEF variants -- on four VL tasks highlight that unimodal collapse can occur to different degrees and in different directions, contradicting the wide-spread assumption that unimodal collapse is one-sided. Based on our results, we recommend MM-SHAP for analysing multimodal tasks, to diagnose and guide progress towards multimodal integration. Code available at urlhttps://github.com/Heidelberg-NLP/MM-SHAP.