paper-with-me

홈 › Papers

A Concept-Based Explainability Framework for Large Multimodal Models

2024-06-12 · Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Alasdair Newson, Matthieu Cord

Large multimodal models (LMMs) combine unimodal encoders and large language models (LLMs) to perform multimodal tasks. Despite recent advancements towards the interpretability of these models, understanding internal representations of LMMs remains largely a mystery. In this paper, we present a novel framework for the interpretation of LMMs. We propose a dictionary learning based approach, applied to the representation of tokens. The elements of the learned dictionary correspond to our proposed concepts. We show that these concepts are well semantically grounded in both vision and text. Thus we refer to these as ``multi-modal concepts''. We qualitatively and quantitatively evaluate the results of the learnt concepts. We show that the extracted multimodal concepts are useful to interpret representations of test samples. Finally, we evaluate the disentanglement between different concepts and the quality of grounding concepts visually and textually. Our code is publicly available at https://github.com/mshukor/xl-vlms

📄 PDF Abstract BibTeX arXiv:2406.08074

Code (1)

mshukor/xl-vlms 공식 구현 pytorch

Tasks

Dictionary LearningDisentanglement

Similar Papers 제목 키워드 기반

Enhancing Explainability in Multimodal Large Language Models Using Ontological Context

2024-09-27 · Jihen Amara, Birgitta König-Ries, Sheeba Samuel

Recently, there has been a growing interest in Multimodal Large Language Models (MLLMs) due to their remarkable potential in various tasks integrating different modalities, such as image and text, as well as applications…

Image CaptioningQuestion AnsweringVisual Question Answering

Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

2025-02-19 · Yucheng Shi, Quanzheng Li, Jin Sun, Xiang Li 외

Large multimodal models (LMMs) have shown impressive capabilities in a wide range of visual tasks. However, they often struggle with fine-grained visual reasoning, failing to identify domain-specific objectives and provi…

Fine-Grained Visual RecognitionPneumonia DetectionVisual Reasoning

CofiPara: A Coarse-to-fine Paradigm for Multimodal Sarcasm Target Identification with Large Multimodal Models

2024-05-01 · Hongzhan Lin, Zixin Chen, Ziyang Luo, Mingfei Cheng 외

Social media abounds with multimodal sarcasm, and identifying sarcasm targets is particularly challenging due to the implicit incongruity not directly evident in the text and image modalities. Current methods for Multimo…

Language ModelingLanguage ModellingMultimodal ReasoningSarcasm Detection+1

Analyzing Fine-tuning Representation Shift for Multimodal LLMs Steering alignment

2025-01-06 · Pegah Khayatan, Mustafa Shukor, Jayneel Parekh, Matthieu Cord

Multimodal LLMs have reached remarkable levels of proficiency in understanding multimodal inputs, driving extensive research to develop increasingly powerful models. However, much less attention has been paid to understa…

Unifying Model Explainability and Robustness via Machine-Checkable Concepts

2020-07-01 · Vedant Nanda, Till Speicher, John P. Dickerson, Krishna P. Gummadi 외

As deep neural networks (DNNs) get adopted in an ever-increasing number of applications, explainability has emerged as a crucial desideratum for these models. In many real-world tasks, one of the principal reasons for re…