Unveiling Visual Perception in Language Models: An Attention Head Analysis Approach

2024-12-24

Computer Vision and Pattern Recognition

AI Summary

How do language models—lacking explicit visual pretraining—achieve image understanding? Method: We systematically analyze 16 multimodal large language models (MLLMs) spanning four architectural families and four parameter scales. Introducing the concept of “vision-preferring attention heads,” we identify such heads via attention behavior analysis, statistical modeling of attention weights, and cross-scale ablation experiments, empirically validating their strong, consistent focus on visual tokens. Contribution: We are the first to discover and formally define this generalizable, modular visual-perception substructure within LLMs. Our work reveals the pivotal role of attention mechanisms in cross-modal adaptation, demonstrating how vision-preferring heads mediate text–vision alignment. This provides an interpretable, spatially localizable mechanism underlying joint text–vision representation learning, thereby advancing research toward transparent, controllable, and analyzable multimodal foundation models.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable progress in visual understanding. This impressive leap raises a compelling question: how can language models, initially trained solely on linguistic data, effectively interpret and process visual content? This paper aims to address this question with systematic investigation across 4 model families and 4 model scales, uncovering a unique class of attention heads that focus specifically on visual content. Our analysis reveals a strong correlation between the behavior of these attention heads, the distribution of attention weights, and their concentration on visual tokens within the input. These findings enhance our understanding of how LLMs adapt to multimodal tasks, demonstrating their potential to bridge the gap between textual and visual understanding. This work paves the way for the development of AI systems capable of engaging with diverse modalities.

Problem

• Investigating how language models interpret visual content without visual training
• Identifying attention heads specialized in processing visual tokens in multimodal models
• Analyzing correlation between attention mechanisms and visual understanding capabilities

Innovation

• Analyzing attention heads for visual content interpretation
• Correlating attention weights with visual token concentration
• Systematic investigation across multiple model families and scales