<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-leach-2026-still">
    <titleInfo>
        <title>STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xiaohan</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Leach</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>LLM-assisted decompilation improves readability and re-executability, but still underperforms on stripped C++ functions that use the Standard Template Library (STL). Compilation, optimization, and symbol stripping remove or obscure source-level semantics such as container types and library-call structure, while traditional decompiler output often fails to recover them. We present STILL, a structured semantic interface that predicts function-level STL container semantics from stripped control-flow graphs and renders them as compact hints for LLM refinement. On StlBench, STILL predicts common container-level STL semantics, with the strongest cross-dataset results for stable string and vector slices. On stripped HumanEval decompilation, these hints enable DeepSeek-chat refinement to reach 28.4% executability, compared with 17.4% for no-hint refinement and 8.9% for raw Ghidra decompilation; hint utility is downstream-backbone-dependent, with decompilation-specialized models requiring lightweight adaptation to benefit from the same interface.</abstract>
    <identifier type="citekey">wang-leach-2026-still</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1898/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>43272</start>
            <end>43287</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation
%A Wang, Xiaohan
%A Leach, Kevin
%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 wang-leach-2026-still
%X LLM-assisted decompilation improves readability and re-executability, but still underperforms on stripped C++ functions that use the Standard Template Library (STL). Compilation, optimization, and symbol stripping remove or obscure source-level semantics such as container types and library-call structure, while traditional decompiler output often fails to recover them. We present STILL, a structured semantic interface that predicts function-level STL container semantics from stripped control-flow graphs and renders them as compact hints for LLM refinement. On StlBench, STILL predicts common container-level STL semantics, with the strongest cross-dataset results for stable string and vector slices. On stripped HumanEval decompilation, these hints enable DeepSeek-chat refinement to reach 28.4% executability, compared with 17.4% for no-hint refinement and 8.9% for raw Ghidra decompilation; hint utility is downstream-backbone-dependent, with decompilation-specialized models requiring lightweight adaptation to benefit from the same interface.
%U https://aclanthology.org/2026.emnlp-main.1898/
%P 43272-43287

Markdown (Informal)

[STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation](https://aclanthology.org/2026.emnlp-main.1898/) (Wang & Leach, EMNLP 2026)

• STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation (Wang & Leach, EMNLP 2026)

ACL

• Xiaohan Wang and Kevin Leach. 2026. STILL: Recovering Lowered STL Semantics for LLM-assisted C++ Decompilation. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 43272–43287, Budapest, Hungary. Association for Computational Linguistics.