MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model

Jiahao Huo, Yibo Yan, Boren Hu, Yutao Yue, Xuming Hu


Abstract
Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms have yet to be explored. Inspired by multilingual research, we identify domain-specific neurons in multimodal large language models. Specifically, we investigate the distribution of domain-specific neurons and the mechanism of how MLLMs process features from diverse domains. Furthermore, we propose a three-stage framework for language model modules in MLLMs when handling projected image features, and verify this hypothesis using logit lens. Extensive experiments indicate that while current MLLMs exhibit Visual Question Answering (VQA) capability, they may not fully utilize domain-specific information. Manipulating domain-specific neurons properly will result in a 10% change of accuracy at most, shedding light on the development of cross-domain, all-encompassing MLLMs in the future. The source code is available at https://anonymous.4open.science/r/MMNeuron.
Anthology ID:
2024.emnlp-main.387
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6801–6816
Language:
URL:
https://aclanthology.org/2024.emnlp-main.387/
DOI:
10.18653/v1/2024.emnlp-main.387
Bibkey:
Cite (ACL):
Jiahao Huo, Yibo Yan, Boren Hu, Yutao Yue, and Xuming Hu. 2024. MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 6801–6816, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model (Huo et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.387.pdf