<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kovacs-etal-2026-rulechef">
    <titleInfo>
        <title>RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ádám</namePart>
        <namePart type="family">Kovács</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nadia</namePart>
        <namePart type="family">Verdha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Gabor</namePart>
        <namePart type="family">Recski</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 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yimu</namePart>
            <namePart type="family">Wang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yee</namePart>
            <namePart type="given">Man</namePart>
            <namePart type="family">Choi</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Di</namePart>
            <namePart type="family">Wu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Siqi</namePart>
            <namePart type="family">Ouyang</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Mozhgan</namePart>
            <namePart type="given">Nasr</namePart>
            <namePart type="family">Azadani</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Yi</namePart>
            <namePart type="given">R</namePart>
            <namePart type="given">(May)</namePart>
            <namePart type="family">Fung</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">979-8-89176-478-1</identifier>
    </relatedItem>
    <abstract>We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or relation extraction. Rules are generated based on a task description and a set of labeled examples, then they are iteratively improved based both on additional examples and on human feedback over existing rules. RuleChef can also be used to bootstrap rules using the observed input-output pairs from any existing model for a given task. LLMs are used only at learning time, synthesizing rules and iteratively patching them based on failures measured on a held-out split. The result of this process is a fast, deterministic, and inspectable rule system. Preliminary evaluation is performed on both classification and NER tasks. We release RuleChef as open-source software under an Apache 2.0 license.</abstract>
    <identifier type="citekey">kovacs-etal-2026-rulechef</identifier>
    <location>
        <url>https://aclanthology.org/2026.groundlm-1.41/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>513</start>
            <end>530</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules
%A Kovács, Ádám
%A Verdha, Nadia
%A Recski, Gabor
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F kovacs-etal-2026-rulechef
%X We present RuleChef, a framework that uses large language models (LLMs) to generate executable rules for NLP tasks such as text classification, Named Entity Recognition (NER), or relation extraction. Rules are generated based on a task description and a set of labeled examples, then they are iteratively improved based both on additional examples and on human feedback over existing rules. RuleChef can also be used to bootstrap rules using the observed input-output pairs from any existing model for a given task. LLMs are used only at learning time, synthesizing rules and iteratively patching them based on failures measured on a held-out split. The result of this process is a fast, deterministic, and inspectable rule system. Preliminary evaluation is performed on both classification and NER tasks. We release RuleChef as open-source software under an Apache 2.0 license.
%U https://aclanthology.org/2026.groundlm-1.41/
%P 513-530

Markdown (Informal)

[RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules](https://aclanthology.org/2026.groundlm-1.41/) (Kovács et al., GroundLM 2026)

• RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules (Kovács et al., GroundLM 2026)

ACL

• Ádám Kovács, Nadia Verdha, and Gabor Recski. 2026. RuleChef: Grounding LLM Task Knowledge in Human-Editable Rules. In Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026), pages 513–530, Budapest, Hungary. Association for Computational Linguistics.