MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks
This provides a diagnostic tool for researchers and practitioners to analyze and improve multimodal integration in AI systems, though it is incremental as it builds on existing Shapley value methods.
The paper tackles the problem of unimodal collapse in vision and language models, where models exploit biases in individual modalities rather than integrating multimodal information, and proposes MM-SHAP, a Shapley value-based metric that quantifies modality contributions, revealing that collapse can vary in degree and direction across models and tasks.
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 \url{https://github.com/Heidelberg-NLP/MM-SHAP}.