<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2025-sacl">
    <titleInfo>
        <title>SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Dhruv</namePart>
        <namePart type="family">Gupta</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gayathri</namePart>
        <namePart type="given">Ganesh</namePart>
        <namePart type="family">Lakshmy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yiqing</namePart>
        <namePart type="family">Xie</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>Findings of the Association for Computational Linguistics: EMNLP 2025</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">979-8-89176-335-7</identifier>
    </relatedItem>
    <abstract>In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features while preserving code functionality. Our discoveries include: (1) although trained on code, current retrievers heavily rely on surface-level textual features (e.g., docstrings, identifier names), and (2) they exhibit a strong bias towards well-documented code, even if the documentation is irrelevant. Based on our discoveries, we propose SACL, a framework that enriches textual information and reduces bias by augmenting code or structural knowledge with semantic information. Extensive experiments show that SACL substantially improves code retrieval (e.g., by 12.8% / 9.4% / 7.0% Recall@1 on HumanEval / MBPP / SWE-Bench-Lite), which also leads to better code generation performance (e.g., by 4.88% Pass@1 on HumanEval).</abstract>
    <identifier type="citekey">gupta-etal-2025-sacl</identifier>
    <location>
        <url>https://aclanthology.org/2025.findings-emnlp.1365/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>25052</start>
            <end>25065</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization
%A Gupta, Dhruv
%A Lakshmy, Gayathri Ganesh
%A Xie, Yiqing
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F gupta-etal-2025-sacl
%X In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features while preserving code functionality. Our discoveries include: (1) although trained on code, current retrievers heavily rely on surface-level textual features (e.g., docstrings, identifier names), and (2) they exhibit a strong bias towards well-documented code, even if the documentation is irrelevant. Based on our discoveries, we propose SACL, a framework that enriches textual information and reduces bias by augmenting code or structural knowledge with semantic information. Extensive experiments show that SACL substantially improves code retrieval (e.g., by 12.8% / 9.4% / 7.0% Recall@1 on HumanEval / MBPP / SWE-Bench-Lite), which also leads to better code generation performance (e.g., by 4.88% Pass@1 on HumanEval).
%U https://aclanthology.org/2025.findings-emnlp.1365/
%P 25052-25065

Markdown (Informal)

[SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization](https://aclanthology.org/2025.findings-emnlp.1365/) (Gupta et al., Findings 2025)

• SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization (Gupta et al., Findings 2025)

ACL

• Dhruv Gupta, Gayathri Ganesh Lakshmy, and Yiqing Xie. 2025. SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localization. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 25052–25065, Suzhou, China. Association for Computational Linguistics.