<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gui-etal-2026-sve">
    <titleInfo>
        <title>SVE-Loom: Improving Session-Level Reliability for Natural-Language-to-SVE Code Generation with Bounded Feedback</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Haoyuan</namePart>
        <namePart type="family">Gui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongjiao</namePart>
        <namePart type="family">Sheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yifan</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huiyuan</namePart>
        <namePart type="family">Li</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>Findings of the Association for Computational Linguistics: EMNLP 2026</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Architecture-specific vector programming remains a difficult frontier for language models: an implementation can satisfy surface syntax yet fail because of a hallucinated intrinsic, an invalid predicate shape, a sizeless-type misuse, or a subtle tail-handling error. This work studies NL2SVE, a function-level code generation problem that maps natural-language specifications and fixed C/C++ signatures to ARM Scalable Vector Extension (SVE) implementations. We introduce SVE-Loom, a model-agnostic generation-and-repair framework that operates within a bounded compile-and-run feedback session. SVE-Loom combines ACLE schema repair, execution feedback, and reference-assisted Regional Semantic Bootstrap when scalar semantics are available. From an initial prompt under a bounded feedback budget, wrapped models using SVE-Loom achieve higher success rates, producing more legal and correct SVE implementations across evaluation benchmarks. We further mitigate the scarcity of public SVE supervision by constructing a NL2SVE corpus from GitHub-mined SVE code, template-generated kernels, and SVE-Loom-guided API-model candidates. This third layer makes the corpus extensible: scalar references or capability gaps can be converted into NL-to-SVE examples, while candidate SVE implementations are retained only after schema checks, compilation, execution testing, speedup measurement, and human audit.</abstract>
    <identifier type="citekey">gui-etal-2026-sve</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1457/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>31013</start>
            <end>31029</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SVE-Loom: Improving Session-Level Reliability for Natural-Language-to-SVE Code Generation with Bounded Feedback
%A Gui, Haoyuan
%A Sheng, Hongjiao
%A Zhang, Yifan
%A Li, Huiyuan
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F gui-etal-2026-sve
%X Architecture-specific vector programming remains a difficult frontier for language models: an implementation can satisfy surface syntax yet fail because of a hallucinated intrinsic, an invalid predicate shape, a sizeless-type misuse, or a subtle tail-handling error. This work studies NL2SVE, a function-level code generation problem that maps natural-language specifications and fixed C/C++ signatures to ARM Scalable Vector Extension (SVE) implementations. We introduce SVE-Loom, a model-agnostic generation-and-repair framework that operates within a bounded compile-and-run feedback session. SVE-Loom combines ACLE schema repair, execution feedback, and reference-assisted Regional Semantic Bootstrap when scalar semantics are available. From an initial prompt under a bounded feedback budget, wrapped models using SVE-Loom achieve higher success rates, producing more legal and correct SVE implementations across evaluation benchmarks. We further mitigate the scarcity of public SVE supervision by constructing a NL2SVE corpus from GitHub-mined SVE code, template-generated kernels, and SVE-Loom-guided API-model candidates. This third layer makes the corpus extensible: scalar references or capability gaps can be converted into NL-to-SVE examples, while candidate SVE implementations are retained only after schema checks, compilation, execution testing, speedup measurement, and human audit.
%U https://aclanthology.org/2026.findings-emnlp.1457/
%P 31013-31029

Markdown (Informal)

[SVE-Loom: Improving Session-Level Reliability for Natural-Language-to-SVE Code Generation with Bounded Feedback](https://aclanthology.org/2026.findings-emnlp.1457/) (Gui et al., Findings 2026)

• SVE-Loom: Improving Session-Level Reliability for Natural-Language-to-SVE Code Generation with Bounded Feedback (Gui et al., Findings 2026)

ACL

• Haoyuan Gui, Hongjiao Sheng, Yifan Zhang, and Huiyuan Li. 2026. SVE-Loom: Improving Session-Level Reliability for Natural-Language-to-SVE Code Generation with Bounded Feedback. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 31013–31029, Budapest, Hungary. Association for Computational Linguistics.