@inproceedings{fuente-etal-2025-guidex,
title = "{GUIDEX}: Guided Synthetic Data Generation for Zero-Shot Information Extraction",
author = "Fuente, Neil De La and
Sainz, Oscar and
Garc{\'i}a-Ferrero, Iker and
Agirre, Eneko",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.1245/",
doi = "10.18653/v1/2025.findings-acl.1245",
pages = "24248--24262",
ISBN = "979-8-89176-256-5",
abstract = "Information Extraction (IE) systems are traditionally domain-specific, requiring costlyadaptation that involves expert schema design,data annotation, and model training. WhileLarge Language Models have shown promisein zero-shot IE, performance degrades significantly in unseen domains where label definitions differ. This paper introduces GUIDEX,a novel method that automatically definesdomain-specific schemas, infers guidelines,and generates synthetically labeled instances,allowing for better out-of-domain generalization. Fine-tuning Llama 3.1 with GUIDEXsets a new state-of-the-art across seven zeroshot Named Entity Recognition benchmarks.Models trained with GUIDEX gain up to 7 F1points over previous methods without humanlabeled data, and nearly 2 F1 points higherwhen combined with it. Models trained onGUIDEX demonstrate enhanced comprehension of complex, domain-specific annotationschemas. Code, models, and synthetic datasetsare available at neilus03.github.io/guidex.com"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fuente-etal-2025-guidex">
<titleInfo>
<title>GUIDEX: Guided Synthetic Data Generation for Zero-Shot Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Neil</namePart>
<namePart type="given">De</namePart>
<namePart type="given">La</namePart>
<namePart type="family">Fuente</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oscar</namePart>
<namePart type="family">Sainz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iker</namePart>
<namePart type="family">García-Ferrero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Information Extraction (IE) systems are traditionally domain-specific, requiring costlyadaptation that involves expert schema design,data annotation, and model training. WhileLarge Language Models have shown promisein zero-shot IE, performance degrades significantly in unseen domains where label definitions differ. This paper introduces GUIDEX,a novel method that automatically definesdomain-specific schemas, infers guidelines,and generates synthetically labeled instances,allowing for better out-of-domain generalization. Fine-tuning Llama 3.1 with GUIDEXsets a new state-of-the-art across seven zeroshot Named Entity Recognition benchmarks.Models trained with GUIDEX gain up to 7 F1points over previous methods without humanlabeled data, and nearly 2 F1 points higherwhen combined with it. Models trained onGUIDEX demonstrate enhanced comprehension of complex, domain-specific annotationschemas. Code, models, and synthetic datasetsare available at neilus03.github.io/guidex.com</abstract>
<identifier type="citekey">fuente-etal-2025-guidex</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.1245</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.1245/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>24248</start>
<end>24262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GUIDEX: Guided Synthetic Data Generation for Zero-Shot Information Extraction
%A Fuente, Neil De La
%A Sainz, Oscar
%A García-Ferrero, Iker
%A Agirre, Eneko
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F fuente-etal-2025-guidex
%X Information Extraction (IE) systems are traditionally domain-specific, requiring costlyadaptation that involves expert schema design,data annotation, and model training. WhileLarge Language Models have shown promisein zero-shot IE, performance degrades significantly in unseen domains where label definitions differ. This paper introduces GUIDEX,a novel method that automatically definesdomain-specific schemas, infers guidelines,and generates synthetically labeled instances,allowing for better out-of-domain generalization. Fine-tuning Llama 3.1 with GUIDEXsets a new state-of-the-art across seven zeroshot Named Entity Recognition benchmarks.Models trained with GUIDEX gain up to 7 F1points over previous methods without humanlabeled data, and nearly 2 F1 points higherwhen combined with it. Models trained onGUIDEX demonstrate enhanced comprehension of complex, domain-specific annotationschemas. Code, models, and synthetic datasetsare available at neilus03.github.io/guidex.com
%R 10.18653/v1/2025.findings-acl.1245
%U https://aclanthology.org/2025.findings-acl.1245/
%U https://doi.org/10.18653/v1/2025.findings-acl.1245
%P 24248-24262
Markdown (Informal)
[GUIDEX: Guided Synthetic Data Generation for Zero-Shot Information Extraction](https://aclanthology.org/2025.findings-acl.1245/) (Fuente et al., Findings 2025)
ACL