<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2024-enhancing">
    <titleInfo>
        <title>Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jingyuan</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dapeng</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yajing</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rongjun</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhiyong</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Wei</namePart>
        <namePart type="family">Peng</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>A Large Language Model (LLM) tends to generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt. To achieve semantic consistency of an LLM, one of the key approaches is to finetune the model with prompt-output pairs with semantically equivalent meanings. Despite its effectiveness, a data-driven finetuning method incurs substantial computation costs in data preparation and model optimization. In this regime, an LLM is treated as a “black box”, restricting our ability to gain deeper insights into its internal mechanism. In this paper, we are motivated to enhance the semantic consistency of LLMs through a more interpretable method (i.e., model editing) to this end. We first identify the model components (i.e., attention heads) that have a key impact on the semantic consistency of an LLM. We subsequently inject biases into the output of these model components along the semantic-consistency activation direction. It is noteworthy that these modifications are cost-effective, without reliance on mass manipulations of the original model parameters. Through comprehensive experiments on the constructed NLU and open-source NLG datasets, our method demonstrates significant improvements in the semantic consistency and task performance of LLMs. Additionally, our method exhibits promising generalization capabilities by performing well on tasks beyond the primary tasks.</abstract>
    <identifier type="citekey">yang-etal-2024-enhancing</identifier>
    <location>
        <url>https://aclanthology.org/2024.findings-acl.199</url>
    </location>
    <part>
        <date>2024-08</date>
        <extent unit="page">
            <start>3343</start>
            <end>3353</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
%A Yang, Jingyuan
%A Chen, Dapeng
%A Sun, Yajing
%A Li, Rongjun
%A Feng, Zhiyong
%A Peng, Wei
%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 yang-etal-2024-enhancing
%X A Large Language Model (LLM) tends to generate inconsistent and sometimes contradictory outputs when presented with a prompt that has equivalent semantics but is expressed differently from the original prompt. To achieve semantic consistency of an LLM, one of the key approaches is to finetune the model with prompt-output pairs with semantically equivalent meanings. Despite its effectiveness, a data-driven finetuning method incurs substantial computation costs in data preparation and model optimization. In this regime, an LLM is treated as a “black box”, restricting our ability to gain deeper insights into its internal mechanism. In this paper, we are motivated to enhance the semantic consistency of LLMs through a more interpretable method (i.e., model editing) to this end. We first identify the model components (i.e., attention heads) that have a key impact on the semantic consistency of an LLM. We subsequently inject biases into the output of these model components along the semantic-consistency activation direction. It is noteworthy that these modifications are cost-effective, without reliance on mass manipulations of the original model parameters. Through comprehensive experiments on the constructed NLU and open-source NLG datasets, our method demonstrates significant improvements in the semantic consistency and task performance of LLMs. Additionally, our method exhibits promising generalization capabilities by performing well on tasks beyond the primary tasks.
%U https://aclanthology.org/2024.findings-acl.199
%P 3343-3353

Markdown (Informal)

[Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach](https://aclanthology.org/2024.findings-acl.199) (Yang et al., Findings 2024)

• Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach (Yang et al., Findings 2024)

ACL

• Jingyuan Yang, Dapeng Chen, Yajing Sun, Rongjun Li, Zhiyong Feng, and Wei Peng. 2024. Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach. In Findings of the Association for Computational Linguistics ACL 2024, pages 3343–3353, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.