@inproceedings{zhang-etal-2025-survey,
title = "A Survey of Generative Information Extraction",
author = "Zhang, Zikang and
You, Wangjie and
Wu, Tianci and
Wang, Xinrui and
Li, Juntao and
Zhang, Min",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.324/",
pages = "4840--4870",
abstract = "Generative information extraction (Generative IE) aims to generate structured text sequences from unstructured text using a generative framework. Scaling in model size yields variations in adaptation and generalization, and also drives fundamental shifts in the techniques and approaches used within this domain. In this survey, we first review generative information extraction (IE) methods based on pre-trained language models (PLMs) and large language models (LLMs), focusing on their adaptation and generalization capabilities. We also discuss the connection between these methods and these two aspects. Furthermore, to balance task performance with the substantial computational demands associated with LLMs, we emphasize the importance of model collaboration. Finally, given the advanced capabilities of LLMs, we explore methods for integrating diverse IE tasks into unified models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2025-survey">
<titleInfo>
<title>A Survey of Generative Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zikang</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wangjie</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianci</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinrui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juntao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generative information extraction (Generative IE) aims to generate structured text sequences from unstructured text using a generative framework. Scaling in model size yields variations in adaptation and generalization, and also drives fundamental shifts in the techniques and approaches used within this domain. In this survey, we first review generative information extraction (IE) methods based on pre-trained language models (PLMs) and large language models (LLMs), focusing on their adaptation and generalization capabilities. We also discuss the connection between these methods and these two aspects. Furthermore, to balance task performance with the substantial computational demands associated with LLMs, we emphasize the importance of model collaboration. Finally, given the advanced capabilities of LLMs, we explore methods for integrating diverse IE tasks into unified models.</abstract>
<identifier type="citekey">zhang-etal-2025-survey</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.324/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>4840</start>
<end>4870</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey of Generative Information Extraction
%A Zhang, Zikang
%A You, Wangjie
%A Wu, Tianci
%A Wang, Xinrui
%A Li, Juntao
%A Zhang, Min
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F zhang-etal-2025-survey
%X Generative information extraction (Generative IE) aims to generate structured text sequences from unstructured text using a generative framework. Scaling in model size yields variations in adaptation and generalization, and also drives fundamental shifts in the techniques and approaches used within this domain. In this survey, we first review generative information extraction (IE) methods based on pre-trained language models (PLMs) and large language models (LLMs), focusing on their adaptation and generalization capabilities. We also discuss the connection between these methods and these two aspects. Furthermore, to balance task performance with the substantial computational demands associated with LLMs, we emphasize the importance of model collaboration. Finally, given the advanced capabilities of LLMs, we explore methods for integrating diverse IE tasks into unified models.
%U https://aclanthology.org/2025.coling-main.324/
%P 4840-4870
Markdown (Informal)
[A Survey of Generative Information Extraction](https://aclanthology.org/2025.coling-main.324/) (Zhang et al., COLING 2025)
ACL
- Zikang Zhang, Wangjie You, Tianci Wu, Xinrui Wang, Juntao Li, and Min Zhang. 2025. A Survey of Generative Information Extraction. In Proceedings of the 31st International Conference on Computational Linguistics, pages 4840–4870, Abu Dhabi, UAE. Association for Computational Linguistics.