<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-ananiadou-2024-neuron">
    <titleInfo>
        <title>Neuron-Level Knowledge Attribution in Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Zeping</namePart>
        <namePart type="family">Yu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sophia</namePart>
        <namePart type="family">Ananiadou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yaser</namePart>
            <namePart type="family">Al-Onaizan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mohit</namePart>
            <namePart type="family">Bansal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yun-Nung</namePart>
            <namePart type="family">Chen</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Miami, Florida, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuron level. In this paper, we propose a static method for pinpointing significant neurons. Compared to seven other methods, our approach demonstrates superior performance across three metrics. Additionally, since most static methods typically only identify “value neurons” directly contributing to the final prediction, we propose a method for identifying “query neurons” which activate these “value neurons”. Finally, we apply our methods to analyze six types of knowledge across both attention and feed-forward network (FFN) layers. Our method and analysis are helpful for understanding the mechanisms of knowledge storage and set the stage for future research in knowledge editing. The code is available on https://github.com/zepingyu0512/neuron-attribution.</abstract>
    <identifier type="citekey">yu-ananiadou-2024-neuron</identifier>
    <location>
        <url>https://aclanthology.org/2024.emnlp-main.191</url>
    </location>
    <part>
        <date>2024-11</date>
        <extent unit="page">
            <start>3267</start>
            <end>3280</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Neuron-Level Knowledge Attribution in Large Language Models
%A Yu, Zeping
%A Ananiadou, Sophia
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F yu-ananiadou-2024-neuron
%X Identifying important neurons for final predictions is essential for understanding the mechanisms of large language models. Due to computational constraints, current attribution techniques struggle to operate at neuron level. In this paper, we propose a static method for pinpointing significant neurons. Compared to seven other methods, our approach demonstrates superior performance across three metrics. Additionally, since most static methods typically only identify “value neurons” directly contributing to the final prediction, we propose a method for identifying “query neurons” which activate these “value neurons”. Finally, we apply our methods to analyze six types of knowledge across both attention and feed-forward network (FFN) layers. Our method and analysis are helpful for understanding the mechanisms of knowledge storage and set the stage for future research in knowledge editing. The code is available on https://github.com/zepingyu0512/neuron-attribution.
%U https://aclanthology.org/2024.emnlp-main.191
%P 3267-3280

Markdown (Informal)

[Neuron-Level Knowledge Attribution in Large Language Models](https://aclanthology.org/2024.emnlp-main.191) (Yu & Ananiadou, EMNLP 2024)

• Neuron-Level Knowledge Attribution in Large Language Models (Yu & Ananiadou, EMNLP 2024)

ACL

• Zeping Yu and Sophia Ananiadou. 2024. Neuron-Level Knowledge Attribution in Large Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 3267–3280, Miami, Florida, USA. Association for Computational Linguistics.