<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pan-etal-2024-finding">
    <titleInfo>
        <title>Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haowen</namePart>
        <namePart type="family">Pan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yixin</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaozhi</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xun</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Meng</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics ACL 2024</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Lun-Wei</namePart>
            <namePart type="family">Ku</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Andre</namePart>
            <namePart type="family">Martins</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Vivek</namePart>
            <namePart type="family">Srikumar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia and industry. In this paper, we propose a novel method to identify key neurons for interpretability — how multi-modal LLMs bridge visual and textual concepts for captioning. Our method improves conventional works upon efficiency and applied range by removing needs of costly gradient computation. Based on those identified neurons, we further design a multi-modal knowledge editing method, beneficial to mitigate sensitive words or hallucination. For rationale of our design, we provide theoretical assumption. For empirical evaluation, we have conducted extensive quantitative and qualitative experiments. The results not only validate the effectiveness of our methods, but also offer insightful findings that highlight three key properties of multi-modal neurons: sensitivity, specificity and causal-effect, to shed light for future research.</abstract>
    <identifier type="citekey">pan-etal-2024-finding</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.60</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>1012</start>
            <end>1037</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
%A Pan, Haowen
%A Cao, Yixin
%A Wang, Xiaozhi
%A Yang, Xun
%A Wang, Meng
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F pan-etal-2024-finding
%X Understanding the internal mechanisms by which multi-modal large language models (LLMs) interpret different modalities and integrate cross-modal representations is becoming increasingly critical for continuous improvements in both academia and industry. In this paper, we propose a novel method to identify key neurons for interpretability — how multi-modal LLMs bridge visual and textual concepts for captioning. Our method improves conventional works upon efficiency and applied range by removing needs of costly gradient computation. Based on those identified neurons, we further design a multi-modal knowledge editing method, beneficial to mitigate sensitive words or hallucination. For rationale of our design, we provide theoretical assumption. For empirical evaluation, we have conducted extensive quantitative and qualitative experiments. The results not only validate the effectiveness of our methods, but also offer insightful findings that highlight three key properties of multi-modal neurons: sensitivity, specificity and causal-effect, to shed light for future research.
%U https://aclanthology.org/2024.findings-acl.60
%P 1012-1037

Markdown (Informal)

[Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers](https://aclanthology.org/2024.findings-acl.60) (Pan et al., Findings 2024)

• Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers (Pan et al., Findings 2024)

ACL

• Haowen Pan, Yixin Cao, Xiaozhi Wang, Xun Yang, and Meng Wang. 2024. Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers. In Findings of the Association for Computational Linguistics ACL 2024, pages 1012–1037, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.