<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2025-co">
    <titleInfo>
        <title>Co-Eval: Augmenting LLM-based Evaluation with Machine Metrics</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ling-I</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Weijie</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Minyu</namePart>
        <namePart type="family">Chen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianxin</namePart>
        <namePart type="family">Xue</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Guoqiang</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Large language models (LLMs) are increasingly used as evaluators in natural language generation tasks, offering advantages in scalability and interpretability over traditional evaluation methods. However, existing LLM-based evaluations often suffer from biases and misalignment, particularly in domain-specific tasks, due to limited functional understanding and knowledge gaps. To address these challenges, we first investigate the relationship between an LLM-based evaluator’s familiarity with the target task and its evaluation performance. We then introduce the Co-Eval framework, which leverages a criteria planner model and optimized machine metrics to enhance the scalability and fairness of LLM-based evaluation. Experimental results on both general and domain-specific tasks demonstrate that Co-Eval reduces biases, achieving up to a 0.4903 reduction in self-preference bias, and improves alignment with human preferences, with gains of up to 0.324 in Spearman correlation.</abstract>
    <identifier type="citekey">wu-etal-2025-co</identifier>
    <identifier type="doi">10.18653/v1/2025.emnlp-main.1307</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.1307/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>25754</start>
            <end>25776</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Co-Eval: Augmenting LLM-based Evaluation with Machine Metrics
%A Wu, Ling-I
%A Wu, Weijie
%A Chen, Minyu
%A Xue, Jianxin
%A Li, Guoqiang
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F wu-etal-2025-co
%X Large language models (LLMs) are increasingly used as evaluators in natural language generation tasks, offering advantages in scalability and interpretability over traditional evaluation methods. However, existing LLM-based evaluations often suffer from biases and misalignment, particularly in domain-specific tasks, due to limited functional understanding and knowledge gaps. To address these challenges, we first investigate the relationship between an LLM-based evaluator’s familiarity with the target task and its evaluation performance. We then introduce the Co-Eval framework, which leverages a criteria planner model and optimized machine metrics to enhance the scalability and fairness of LLM-based evaluation. Experimental results on both general and domain-specific tasks demonstrate that Co-Eval reduces biases, achieving up to a 0.4903 reduction in self-preference bias, and improves alignment with human preferences, with gains of up to 0.324 in Spearman correlation.
%R 10.18653/v1/2025.emnlp-main.1307
%U https://aclanthology.org/2025.emnlp-main.1307/
%U https://doi.org/10.18653/v1/2025.emnlp-main.1307
%P 25754-25776

Markdown (Informal)

[Co-Eval: Augmenting LLM-based Evaluation with Machine Metrics](https://aclanthology.org/2025.emnlp-main.1307/) (Wu et al., EMNLP 2025)

• Co-Eval: Augmenting LLM-based Evaluation with Machine Metrics (Wu et al., EMNLP 2025)

ACL

• Ling-I Wu, Weijie Wu, Minyu Chen, Jianxin Xue, and Guoqiang Li. 2025. Co-Eval: Augmenting LLM-based Evaluation with Machine Metrics. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 25754–25776, Suzhou, China. Association for Computational Linguistics.