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

• URL: http://arxiv.org/abs/2406.04236v1
• Date: Thu, 6 Jun 2024 16:35:36 GMT
• Title: Understanding Information Storage and Transfer in Multi-modal Large Language Models
• Authors: Samyadeep Basu, Martin Grayson, Cecily Morrison, Besmira Nushi, Soheil Feizi, Daniela Massiceti,
• Abstract summary: We study how Multi-modal Large Language Models process information in a factual visual question answering task. Key findings show that these MLLMs rely on self-attention blocks in much earlier layers for information storage. We introduce MultEdit, a model-editing algorithm that can correct errors and insert new long-tailed information into MLLMs.
• Score: 51.20840103605018
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• LLaVA-KD: A Framework of Distilling Multimodal Large Language Models [70.19607283302712]
  We propose a novel framework to transfer knowledge from l-MLLM to s-MLLM. Specifically, we introduce Multimodal Distillation (MDist) to minimize the divergence between the visual-textual output distributions of l-MLLM and s-MLLM. We also propose a three-stage training scheme to fully exploit the potential of s-MLLM.
  arXiv  Detail & Related papers  (2024-10-21T17:41:28Z)
• Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering [108.2131720470005]
  Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. They often struggle to fully comprehend and effectively utilize their input contexts, resulting in responses that are unfaithful or hallucinated. We propose AutoPASTA, a method that automatically identifies key contextual information and explicitly highlights it by steering an LLM's attention scores.
  arXiv  Detail & Related papers  (2024-09-16T23:52:41Z)
• Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models [5.5712075816599]
  Multimodal Large Language Models (MLLMs) have made significant progress in bridging the gap between visual and language modalities. However, hallucinations in MLLMs, where the generated text does not align with image content, continue to be a major challenge. We introduce a novel training-free method, named Piculet, for enhancing the input representation of MLLMs.
  arXiv  Detail & Related papers  (2024-08-02T04:34:37Z)
• LLAVADI: What Matters For Multimodal Large Language Models Distillation [77.73964744238519]
  In this work, we do not propose a new efficient model structure or train small-scale MLLMs from scratch. Our studies involve training strategies, model choices, and distillation algorithms in the knowledge distillation process. By evaluating different benchmarks and proper strategy, even a 2.7B small-scale model can perform on par with larger models with 7B or 13B parameters.
  arXiv  Detail & Related papers  (2024-07-28T06:10:47Z)
• The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective [53.48484062444108]
  We find that the development of models and data is not two separate paths but rather interconnected. On the one hand, vaster and higher-quality data contribute to better performance of MLLMs; on the other hand, MLLMs can facilitate the development of data. To promote the data-model co-development for MLLM community, we systematically review existing works related to MLLMs from the data-model co-development perspective.
  arXiv  Detail & Related papers  (2024-07-11T15:08:11Z)
• Rethinking Visual Prompting for Multimodal Large Language Models with External Knowledge [76.45868419402265]
  multimodal large language models (MLLMs) have made significant strides by training on vast high-quality image-text datasets. However, the inherent difficulty in explicitly conveying fine-grained or spatially dense information in text, such as masks, poses a challenge for MLLMs. This paper proposes a new visual prompt approach to integrate fine-grained external knowledge, gleaned from specialized vision models, into MLLMs.
  arXiv  Detail & Related papers  (2024-07-05T17:43:30Z)
• Benchmarking Large Language Models for Molecule Prediction Tasks [7.067145619709089]
  Large Language Models (LLMs) stand at the forefront of a number of Natural Language Processing (NLP) tasks. This paper explores a fundamental question: Can LLMs effectively handle molecule prediction tasks? We identify several classification and regression prediction tasks across six standard molecule datasets. We compare their performance with existing Machine Learning (ML) models, which include text-based models and those specifically designed for analysing the geometric structure of molecules.
  arXiv  Detail & Related papers  (2024-03-08T05:59:56Z)
• The Curious Case of Nonverbal Abstract Reasoning with Multi-Modal Large Language Models [19.213774611556]
  Multi-modal large language models (MLLMs) integrate verbal and visual information. Despite the revolutionizing prospect of MLLMs, our understanding of their reasoning abilities is limited. In this study, we assess the nonverbal abstract reasoning abilities of open-source and closed-source MLLMs.
  arXiv  Detail & Related papers  (2024-01-22T16:57:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.