<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="giroh-etal-2025-syntact">
    <titleInfo>
        <title>\ensuremath&lt;SYNTACT\ensuremath&gt;: Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sachin</namePart>
        <namePart type="given">Kumar</namePart>
        <namePart type="family">Giroh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Pushpendu</namePart>
        <namePart type="family">Ghosh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aryan</namePart>
        <namePart type="family">Jain</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Harshal</namePart>
        <namePart type="given">Giridhari</namePart>
        <namePart type="family">Paunikar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Aditi</namePart>
        <namePart type="family">Rastogi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Promod</namePart>
        <namePart type="family">Yenigalla</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anish</namePart>
        <namePart type="family">Nediyanchath</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Saloni</namePart>
            <namePart type="family">Potdar</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Lina</namePart>
            <namePart type="family">Rojas-Barahona</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastien</namePart>
            <namePart type="family">Montella</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou (China)</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-333-3</identifier>
    </relatedItem>
    <abstract>This paper introduces \ensuremath&lt;SYNTACT\ensuremath&gt;, a three-stage multi agent LLM framework designed to transform unstructured and ambiguous Standard Operating Procedure (SOP) into a structured plan and an executable code template. Unstructured SOPs—common across industries such as finance, retail, and logistics—frequently suffer from ambiguity, missing information, and inconsistency, all of which hinder automation. SYNTACT addresses this through: (1) a Clarifier module that disambiguate the SOP using large language models, internal knowledge base (RAG) and human-in-the-loop , (2) a Planner that converts refined natural language instructions into a structured plan of hierarchical task flows through function (API) tagging, conditional branches and human-in-the-loop check-points, and (3) an Implementor that generates executable code fragments or pseudocode templates. We evaluate SYNTACT on real-world SOPs and synthetic variants, demonstrating an 88.4% end-to-end accuracy and a significant reduction in inconsistency compared to leading LLM baselines. Ablation studies highlight the necessity of each component, with performance dropping notably when modules are removed.Our findings show that structured multi-agent pipelines like SYNTACT can meaningfully improve consistency, reduce manual effort, and accelerate automation at scale.</abstract>
    <identifier type="citekey">giroh-etal-2025-syntact</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-industry.163/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>2367</start>
            <end>2376</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T \ensuremath<SYNTACT\ensuremath>: Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates
%A Giroh, Sachin Kumar
%A Ghosh, Pushpendu
%A Jain, Aryan
%A Paunikar, Harshal Giridhari
%A Rastogi, Aditi
%A Yenigalla, Promod
%A Nediyanchath, Anish
%Y Potdar, Saloni
%Y Rojas-Barahona, Lina
%Y Montella, Sebastien
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou (China)
%@ 979-8-89176-333-3
%F giroh-etal-2025-syntact
%X This paper introduces \ensuremath<SYNTACT\ensuremath>, a three-stage multi agent LLM framework designed to transform unstructured and ambiguous Standard Operating Procedure (SOP) into a structured plan and an executable code template. Unstructured SOPs—common across industries such as finance, retail, and logistics—frequently suffer from ambiguity, missing information, and inconsistency, all of which hinder automation. SYNTACT addresses this through: (1) a Clarifier module that disambiguate the SOP using large language models, internal knowledge base (RAG) and human-in-the-loop , (2) a Planner that converts refined natural language instructions into a structured plan of hierarchical task flows through function (API) tagging, conditional branches and human-in-the-loop check-points, and (3) an Implementor that generates executable code fragments or pseudocode templates. We evaluate SYNTACT on real-world SOPs and synthetic variants, demonstrating an 88.4% end-to-end accuracy and a significant reduction in inconsistency compared to leading LLM baselines. Ablation studies highlight the necessity of each component, with performance dropping notably when modules are removed.Our findings show that structured multi-agent pipelines like SYNTACT can meaningfully improve consistency, reduce manual effort, and accelerate automation at scale.
%U https://aclanthology.org/2025.emnlp-industry.163/
%P 2367-2376

Markdown (Informal)

[<SYNTACT>: Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates](https://aclanthology.org/2025.emnlp-industry.163/) (Giroh et al., EMNLP 2025)

• : Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates (Giroh et al., EMNLP 2025)

ACL

• Sachin Kumar Giroh, Pushpendu Ghosh, Aryan Jain, Harshal Giridhari Paunikar, Aditi Rastogi, Promod Yenigalla, and Anish Nediyanchath. 2025. : Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2367–2376, Suzhou (China). Association for Computational Linguistics.