Multi-Faceted Multimodal Monosemanticity
This work provides interpretability tools for multimodal AI models, offering insights into modality relationships that benefit downstream applications.
The researchers analyzed interpretable features from CLIP multimodal models to categorize them as vision-only, language-only, or cross-modal, which aligned with human intuition and improved tasks like gender bias reduction and text-to-image generation.
Humans experience the world through multiple modalities, such as, vision, language, and speech, making it natural to explore the commonality and distinctions among them. In this work, we take a data-driven approach to address this question by analyzing interpretable, monosemantic features extracted from deep multimodal models. Specifically, we investigate CLIP, a prominent visual-language representation model trained on massive image-text pairs. Building on prior research in single-modal interpretability, we develop a set of multi-modal interpretability tools and measures designed to disentangle and analyze features learned from CLIP. Specifically, we introduce the Modality Dominance Score (MDS) to attribute each CLIP feature to a specific modality. We then map CLIP features into a more interpretable space, enabling us to categorize them into three distinct classes: vision features (single-modal), language features (single-modal), and visual-language features (cross-modal). Interestingly, this data-driven categorization closely aligns with human intuitive understandings of different modalities. We further show that this modality decomposition can benefit multiple downstream tasks, including reducing bias in gender detection, generating cross-modal adversarial examples, and enabling modal-specific feature control in text-to-image generation. These results indicate that large-scale multimodal models, when equipped with task-agnostic interpretability tools, can offer valuable insights into the relationships between different data modalities.