<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dey-etal-2026-schema">
    <titleInfo>
        <title>Schema-Hierarchical Soft Prompts for Structured Information Extraction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Soumyadeep</namePart>
        <namePart type="family">Dey</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Srikanth</namePart>
        <namePart type="family">Tenneti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bamdev</namePart>
        <namePart type="family">Mishra</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shobhit</namePart>
        <namePart type="family">Niranjan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mayur</namePart>
        <namePart type="family">Datar</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: Industry Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pepa</namePart>
            <namePart type="family">Atanasova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Gholamreza</namePart>
            <namePart type="family">Haffari</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Minghan</namePart>
            <namePart type="family">Wang</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">979-8-89176-460-6</identifier>
    </relatedItem>
    <abstract>Structured information extraction at small-language-model scale is a routine production workload, yet each new task added to a serving stack can demand new task-specific model state. We propose a schema-hierarchical soft prompt: a small learned prefix, trained on a frozen backbone, that gives every JSON-schema node its own slot, orders the slots by the schema, and marks tree depth with learned embeddings. Used alone on the open USPTO-ORD patent task, it recovers most of a LoRA reference’s extraction quality while training more than an order of magnitude fewer parameters, and ablations attribute the gain to depth and schema order rather than token count. Used with a LoRA adapter on an internal booking task, the same slots stabilize one of two held-out categories, so we report this as a bounded mechanism study rather than a general gain. Inference-time slot replacement indicates that position supplies the schema scaffold while learned content stabilizes generation. Measured serving gives a far smaller task artifact and higher throughput than multi-LoRA as interleaved tasks grow. The soft-prompt module is available at https://github.com/microsoft/Hierarchical-Soft-Prompt.</abstract>
    <identifier type="citekey">dey-etal-2026-schema</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.124/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2127</start>
            <end>2148</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Schema-Hierarchical Soft Prompts for Structured Information Extraction
%A Dey, Soumyadeep
%A Tenneti, Srikanth
%A Mishra, Bamdev
%A Niranjan, Shobhit
%A Datar, Mayur
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F dey-etal-2026-schema
%X Structured information extraction at small-language-model scale is a routine production workload, yet each new task added to a serving stack can demand new task-specific model state. We propose a schema-hierarchical soft prompt: a small learned prefix, trained on a frozen backbone, that gives every JSON-schema node its own slot, orders the slots by the schema, and marks tree depth with learned embeddings. Used alone on the open USPTO-ORD patent task, it recovers most of a LoRA reference’s extraction quality while training more than an order of magnitude fewer parameters, and ablations attribute the gain to depth and schema order rather than token count. Used with a LoRA adapter on an internal booking task, the same slots stabilize one of two held-out categories, so we report this as a bounded mechanism study rather than a general gain. Inference-time slot replacement indicates that position supplies the schema scaffold while learned content stabilizes generation. Measured serving gives a far smaller task artifact and higher throughput than multi-LoRA as interleaved tasks grow. The soft-prompt module is available at https://github.com/microsoft/Hierarchical-Soft-Prompt.
%U https://aclanthology.org/2026.emnlp-industry.124/
%P 2127-2148

Markdown (Informal)

[Schema-Hierarchical Soft Prompts for Structured Information Extraction](https://aclanthology.org/2026.emnlp-industry.124/) (Dey et al., EMNLP 2026)

• Schema-Hierarchical Soft Prompts for Structured Information Extraction (Dey et al., EMNLP 2026)

ACL

• Soumyadeep Dey, Srikanth Tenneti, Bamdev Mishra, Shobhit Niranjan, and Mayur Datar. 2026. Schema-Hierarchical Soft Prompts for Structured Information Extraction. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2127–2148, Budapest, Hungary. Association for Computational Linguistics.