<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chu-etal-2026-aegiscodegen">
    <titleInfo>
        <title>AegisCodeGen: Toward Copyright-Aware Code Generation with Runnability-Guided Fusion</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Rui</namePart>
        <namePart type="family">Chu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicole</namePart>
        <namePart type="family">Meng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tanusree</namePart>
        <namePart type="given">Das</namePart>
        <namePart type="family">Tithy</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Thomas</namePart>
        <namePart type="family">Cao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Faysal</namePart>
        <namePart type="given">Hossain</namePart>
        <namePart type="family">Shezan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yingjie</namePart>
        <namePart type="family">Lao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Code large language model introduces copyright risks when models reproduce protected implementations from training data. Existing inference-time copyright-protection methods overlook the power of using the original LLM capability for a runnable code generation. In this paper, we propose AegisCodeGen (ACG), an inference-time copyright-aware controlled generation framework for code LLMs, effectively extending the text copyright protection towards the code generation domain. We argue that code copyright protection should be formulated as a region-aware generation control problem, where the model first identifies where modification is safe and then decides how strongly copyright-aware fusion should be applied. Based on this insight, ACG mainly consists of two stages. Firstly, ACG performs multiple sampling generations to construct an agreement profile over the target program, indicating which regions are more likely to affect core code logic after modification. Secondly, ACG uses this profile to adaptively control fusion strength, applying stronger copyright protection in low-agreement regions and weaker shifts near executable anchors. Through intense experiments, we demonstrate that ACG reduces protected-content reproduction while preserving runability and generation utility, providing a lightweight copyright-aware module that requires neither model retraining nor access to training data.</abstract>
    <identifier type="citekey">chu-etal-2026-aegiscodegen</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.2521/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>57326</start>
            <end>57337</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T AegisCodeGen: Toward Copyright-Aware Code Generation with Runnability-Guided Fusion
%A Chu, Rui
%A Meng, Nicole
%A Tithy, Tanusree Das
%A Cao, Thomas
%A Shezan, Faysal Hossain
%A Lao, Yingjie
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F chu-etal-2026-aegiscodegen
%X Code large language model introduces copyright risks when models reproduce protected implementations from training data. Existing inference-time copyright-protection methods overlook the power of using the original LLM capability for a runnable code generation. In this paper, we propose AegisCodeGen (ACG), an inference-time copyright-aware controlled generation framework for code LLMs, effectively extending the text copyright protection towards the code generation domain. We argue that code copyright protection should be formulated as a region-aware generation control problem, where the model first identifies where modification is safe and then decides how strongly copyright-aware fusion should be applied. Based on this insight, ACG mainly consists of two stages. Firstly, ACG performs multiple sampling generations to construct an agreement profile over the target program, indicating which regions are more likely to affect core code logic after modification. Secondly, ACG uses this profile to adaptively control fusion strength, applying stronger copyright protection in low-agreement regions and weaker shifts near executable anchors. Through intense experiments, we demonstrate that ACG reduces protected-content reproduction while preserving runability and generation utility, providing a lightweight copyright-aware module that requires neither model retraining nor access to training data.
%U https://aclanthology.org/2026.emnlp-main.2521/
%P 57326-57337

Markdown (Informal)

[AegisCodeGen: Toward Copyright-Aware Code Generation with Runnability-Guided Fusion](https://aclanthology.org/2026.emnlp-main.2521/) (Chu et al., EMNLP 2026)

• AegisCodeGen: Toward Copyright-Aware Code Generation with Runnability-Guided Fusion (Chu et al., EMNLP 2026)

ACL

• Rui Chu, Nicole Meng, Tanusree Das Tithy, Thomas Cao, Faysal Hossain Shezan, and Yingjie Lao. 2026. AegisCodeGen: Toward Copyright-Aware Code Generation with Runnability-Guided Fusion. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 57326–57337, Budapest, Hungary. Association for Computational Linguistics.