<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deng-etal-2026-compile">
    <titleInfo>
        <title>Compile by Training: Turning Natural-Language Specifications into Local Neural Functions</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yuntian</namePart>
        <namePart type="family">Deng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pengyu</namePart>
        <namePart type="family">Nie</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Stuart</namePart>
        <namePart type="family">Shieber</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: System Demonstrations</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Sweta</namePart>
            <namePart type="family">Agrawal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Alberto</namePart>
            <namePart type="family">Abad</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">979-8-89176-461-3</identifier>
    </relatedItem>
    <abstract>Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote model for every input introduces repeated cost, latency, and dependency on a provider. We present compile by training, which turns a natural-language specification into a reusable neural function. At compile time, teacher models generate task-specific examples that are used to train a small adapter for a compact interpreter. The resulting function runs without the teachers and can be stored, versioned, and composed like ordinary software. On FuzzyBench-Focus, compile by training reaches 83.6% accuracy, compared with 22.4% for the previous Program-as-Weights compiler, which predicts function weights in a single forward pass. A representative cold compile takes 50.9 seconds on a B300 GPU. We deploy the compiler in a public interactive service and demonstrate compiled functions in a multi-site website helper and a language-controlled 3D avatar.</abstract>
    <identifier type="citekey">deng-etal-2026-compile</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-demos.78/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>830</start>
            <end>839</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Compile by Training: Turning Natural-Language Specifications into Local Neural Functions
%A Deng, Yuntian
%A Nie, Pengyu
%A Shieber, Stuart
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F deng-etal-2026-compile
%X Many recurring text functions are easy to describe but difficult to implement with rules, while calling a large remote model for every input introduces repeated cost, latency, and dependency on a provider. We present compile by training, which turns a natural-language specification into a reusable neural function. At compile time, teacher models generate task-specific examples that are used to train a small adapter for a compact interpreter. The resulting function runs without the teachers and can be stored, versioned, and composed like ordinary software. On FuzzyBench-Focus, compile by training reaches 83.6% accuracy, compared with 22.4% for the previous Program-as-Weights compiler, which predicts function weights in a single forward pass. A representative cold compile takes 50.9 seconds on a B300 GPU. We deploy the compiler in a public interactive service and demonstrate compiled functions in a multi-site website helper and a language-controlled 3D avatar.
%U https://aclanthology.org/2026.emnlp-demos.78/
%P 830-839

Markdown (Informal)

[Compile by Training: Turning Natural-Language Specifications into Local Neural Functions](https://aclanthology.org/2026.emnlp-demos.78/) (Deng et al., EMNLP 2026)

• Compile by Training: Turning Natural-Language Specifications into Local Neural Functions (Deng et al., EMNLP 2026)

ACL

• Yuntian Deng, Pengyu Nie, and Stuart Shieber. 2026. Compile by Training: Turning Natural-Language Specifications into Local Neural Functions. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 830–839, Budapest, Hungary. Association for Computational Linguistics.