@inproceedings{ho-etal-2026-schemarag,
title = "{S}chema{RAG}: Dynamic Large Schema Reduction for {LLM}-driven Structured Information Extraction",
author = "Ho, Sin Yu Bonnie and
Coles, Arlie and
Larsson, Erik and
Marshall, Eric and
Bodenstab, Nathan and
Vozila, Paul",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.78/",
pages = "1114--1127",
ISBN = "979-8-89176-394-4",
abstract = "Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when the target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples (when available). We evaluate SchemaRAG on real-world healthcare and e-commerce datasets. Our results show that SchemaRAG can achieve up to an 8.8{\%} increase in micro-F1, a 47{\%} reduction in latency, and a 48{\%} reduction in token costs, demonstrating its practicality for large-schema extraction."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ho-etal-2026-schemarag">
<titleInfo>
<title>SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sin</namePart>
<namePart type="given">Yu</namePart>
<namePart type="given">Bonnie</namePart>
<namePart type="family">Ho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arlie</namePart>
<namePart type="family">Coles</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Larsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Marshall</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Bodenstab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Vozila</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when the target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples (when available). We evaluate SchemaRAG on real-world healthcare and e-commerce datasets. Our results show that SchemaRAG can achieve up to an 8.8% increase in micro-F1, a 47% reduction in latency, and a 48% reduction in token costs, demonstrating its practicality for large-schema extraction.</abstract>
<identifier type="citekey">ho-etal-2026-schemarag</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.78/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1114</start>
<end>1127</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction
%A Ho, Sin Yu Bonnie
%A Coles, Arlie
%A Larsson, Erik
%A Marshall, Eric
%A Bodenstab, Nathan
%A Vozila, Paul
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F ho-etal-2026-schemarag
%X Extracting structured data from unstructured text using large language models (LLMs) becomes challenging when the target schemas are large and complex. In such cases, including the full schema in the prompt increases cost and latency, risks lost-in-the-middle performance degradation, and can exceed context length limits. We propose SchemaRAG, a retrieval-augmented generation (RAG) framework that dynamically prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples (when available). We evaluate SchemaRAG on real-world healthcare and e-commerce datasets. Our results show that SchemaRAG can achieve up to an 8.8% increase in micro-F1, a 47% reduction in latency, and a 48% reduction in token costs, demonstrating its practicality for large-schema extraction.
%U https://aclanthology.org/2026.acl-industry.78/
%P 1114-1127
Markdown (Informal)
[SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction](https://aclanthology.org/2026.acl-industry.78/) (Ho et al., ACL 2026)
ACL