English

Understanding Information Storage and Transfer in Multi-modal Large Language Models

Computer Vision and Pattern Recognition 2024-06-07 v1

Abstract

Understanding the mechanisms of information storage and transfer in Transformer-based models is important for driving model understanding progress. Recent work has studied these mechanisms for Large Language Models (LLMs), revealing insights on how information is stored in a model's parameters and how information flows to and from these parameters in response to specific prompts. However, these studies have not yet been extended to Multi-modal Large Language Models (MLLMs). Given their expanding capabilities and real-world use, we start by studying one aspect of these models -- how MLLMs process information in a factual visual question answering task. We use a constraint-based formulation which views a visual question as having a set of visual or textual constraints that the model's generated answer must satisfy to be correct (e.g. What movie directed by the director in this photo has won a Golden Globe?). Under this setting, we contribute i) a method that extends causal information tracing from pure language to the multi-modal setting, and ii) VQA-Constraints, a test-bed of 9.7K visual questions annotated with constraints. We use these tools to study two open-source MLLMs, LLaVa and multi-modal Phi-2. Our key findings show that these MLLMs rely on MLP and self-attention blocks in much earlier layers for information storage, compared to LLMs whose mid-layer MLPs are more important. We also show that a consistent small subset of visual tokens output by the vision encoder are responsible for transferring information from the image to these causal blocks. We validate these mechanisms by introducing MultEdit, a model-editing algorithm that can correct errors and insert new long-tailed information into MLLMs by targeting these causal blocks.

Keywords

Cite

@article{arxiv.2406.04236,
  title  = {Understanding Information Storage and Transfer in Multi-modal Large Language Models},
  author = {Samyadeep Basu and Martin Grayson and Cecily Morrison and Besmira Nushi and Soheil Feizi and Daniela Massiceti},
  journal= {arXiv preprint arXiv:2406.04236},
  year   = {2024}
}

Comments

20 pages

R2 v1 2026-06-28T16:56:09.318Z