<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="oh-lee-2026-late">
    <titleInfo>
        <title>Late Code Chunking: A Code Chunking Strategy for Repository-Level Code Completion</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Seungmin</namePart>
        <namePart type="family">Oh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Eunseok</namePart>
        <namePart type="family">Lee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Maria</namePart>
            <namePart type="family">Liakata</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Viviane</namePart>
            <namePart type="given">P</namePart>
            <namePart type="family">Moreira</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jiajun</namePart>
            <namePart type="family">Zhang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">David</namePart>
            <namePart type="family">Jurgens</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">San Diego, California, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-391-3</identifier>
    </relatedItem>
    <abstract>This paper introduces Late Code Chunking (LC²), a chunking strategy designed to improve the semantic understanding of code segments for Large Language Models (LLMs). Repository-level code completion requires predicting the completion of unfinished code by leveraging cross-file context spread across a repository. However, when retrieved fragments have missing semantics—the loss of structural or behavioral information during chunking—LLMs struggle to interpret the target code. To address this, LC² refines retrieved chunks by constructing a dual context: a “Code Retrieval Context” optimized for similarity-based search, and a “Code Comprehension Context” that serves as a late enrichment step through context expansion and augmentation. This dual-context design reduces information loss due to chunking and enhances the ability of LLMs to utilize retrieved code. Additionally, we introduce an Asymmetric Query-Chunk Sizing strategy to further optimize retrieval quality by minimizing query noise. Our experiments demonstrate that LC² provides robust performance gains, achieving a statistically significant 19.7% improvement in Exact Match accuracy on the CrossCodeEval benchmark compared to the best existing chunking method.</abstract>
    <identifier type="citekey">oh-lee-2026-late</identifier>
    <location>
        <url>https://aclanthology.org/2026.acl-short.64/</url>
    </location>
    <part>
        <date>2026-07</date>
        <extent unit="page">
            <start>780</start>
            <end>786</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Late Code Chunking: A Code Chunking Strategy for Repository-Level Code Completion
%A Oh, Seungmin
%A Lee, Eunseok
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-391-3
%F oh-lee-2026-late
%X This paper introduces Late Code Chunking (LC²), a chunking strategy designed to improve the semantic understanding of code segments for Large Language Models (LLMs). Repository-level code completion requires predicting the completion of unfinished code by leveraging cross-file context spread across a repository. However, when retrieved fragments have missing semantics—the loss of structural or behavioral information during chunking—LLMs struggle to interpret the target code. To address this, LC² refines retrieved chunks by constructing a dual context: a “Code Retrieval Context” optimized for similarity-based search, and a “Code Comprehension Context” that serves as a late enrichment step through context expansion and augmentation. This dual-context design reduces information loss due to chunking and enhances the ability of LLMs to utilize retrieved code. Additionally, we introduce an Asymmetric Query-Chunk Sizing strategy to further optimize retrieval quality by minimizing query noise. Our experiments demonstrate that LC² provides robust performance gains, achieving a statistically significant 19.7% improvement in Exact Match accuracy on the CrossCodeEval benchmark compared to the best existing chunking method.
%U https://aclanthology.org/2026.acl-short.64/
%P 780-786

Markdown (Informal)

[Late Code Chunking: A Code Chunking Strategy for Repository-Level Code Completion](https://aclanthology.org/2026.acl-short.64/) (Oh & Lee, ACL 2026)

• Late Code Chunking: A Code Chunking Strategy for Repository-Level Code Completion (Oh & Lee, ACL 2026)

ACL

• Seungmin Oh and Eunseok Lee. 2026. Late Code Chunking: A Code Chunking Strategy for Repository-Level Code Completion. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 780–786, San Diego, California, United States. Association for Computational Linguistics.