<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhiqiang-etal-2025-judge">
    <titleInfo>
        <title>Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mo</namePart>
        <namePart type="family">Zhiqiang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Hua</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jiahui</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuan</namePart>
        <namePart type="family">Liu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shawn</namePart>
        <namePart type="family">Wong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianmin</namePart>
        <namePart type="family">Huang</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>Graph Neural Networks (GNNs) have shown immense potential in improving the performance of large-scale models by effectively incorporating structured relational information. However, current approaches face two key challenges: (1) achieving robust semantic alignment between graph representations and large models, and (2) ensuring interpretability in the generated outputs. To address these challenges, we propose ExGLM (Explainable Graph Language Model), a novel training framework designed to seamlessly integrate graph and language modalities while enhancing transparency. Our framework introduces two core components: (1) a graph-language synergistic alignment module, which aligns graph structures with language model to ensure semantic consistency across modalities; and (2) a judge-and-improve paradigm, which allows the language model to iteratively evaluate, refine, and prioritize responses with higher interpretability, thereby improving both performance and transparency. Extensive experiments conducted on three benchmark datasets—ogbn-arxiv, Cora, and PubMed—demonstrate that ExGLM not only surpasses existing methods in efficiency but also generates outputs that are significantly more interpretable, effectively addressing the primary limitations of current approaches.</abstract>
    <identifier type="citekey">zhiqiang-etal-2025-judge</identifier>
    <identifier type="doi">10.18653/v1/2025.emnlp-main.269</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.269/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>5303</start>
            <end>5320</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models
%A Zhiqiang, Mo
%A Hua, Yang
%A Li, Jiahui
%A Liu, Yuan
%A Wong, Shawn
%A Huang, Jianmin
%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 zhiqiang-etal-2025-judge
%X Graph Neural Networks (GNNs) have shown immense potential in improving the performance of large-scale models by effectively incorporating structured relational information. However, current approaches face two key challenges: (1) achieving robust semantic alignment between graph representations and large models, and (2) ensuring interpretability in the generated outputs. To address these challenges, we propose ExGLM (Explainable Graph Language Model), a novel training framework designed to seamlessly integrate graph and language modalities while enhancing transparency. Our framework introduces two core components: (1) a graph-language synergistic alignment module, which aligns graph structures with language model to ensure semantic consistency across modalities; and (2) a judge-and-improve paradigm, which allows the language model to iteratively evaluate, refine, and prioritize responses with higher interpretability, thereby improving both performance and transparency. Extensive experiments conducted on three benchmark datasets—ogbn-arxiv, Cora, and PubMed—demonstrate that ExGLM not only surpasses existing methods in efficiency but also generates outputs that are significantly more interpretable, effectively addressing the primary limitations of current approaches.
%R 10.18653/v1/2025.emnlp-main.269
%U https://aclanthology.org/2025.emnlp-main.269/
%U https://doi.org/10.18653/v1/2025.emnlp-main.269
%P 5303-5320

Markdown (Informal)

[Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models](https://aclanthology.org/2025.emnlp-main.269/) (Zhiqiang et al., EMNLP 2025)

• Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models (Zhiqiang et al., EMNLP 2025)

ACL

• Mo Zhiqiang, Yang Hua, Jiahui Li, Yuan Liu, Shawn Wong, and Jianmin Huang. 2025. Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 5303–5320, Suzhou, China. Association for Computational Linguistics.