@inproceedings{bao-wang-2024-general,
title = "General Collaborative Framework between Large Language Model and Experts for Universal Information Extraction",
author = "Bao, K and
Wang, Ning",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.4/",
doi = "10.18653/v1/2024.findings-emnlp.4",
pages = "52--77",
abstract = "Recently, unified information extraction has garnered widespread attention from the NLP community, which aims to use a unified paradigm to perform various information extraction tasks. However, prevalent unified IE approaches inevitably encounter challenges such as noise interference, abstract label semantics, and diverse span granularity. In this paper, we first present three problematic assumptions regarding the capabilities of unified information extraction model. Furthermore, we propose the General Collaborative Information Extraction (GCIE) framework to address these challenges in universal information extraction tasks. Specifically, GCIE consists of a general Recognizer as well as multiple task-specific Experts for recognizing predefined types and extracting spans respectively. The Recognizer is a large language model, while the Experts comprise a series of smaller language models. Together, they collaborate in a two-stage pipeline to perform unified information extraction. Extensive empirical experiments on 6 IE tasks and several datasets, validate the effectiveness and generality of our approach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-wang-2024-general">
<titleInfo>
<title>General Collaborative Framework between Large Language Model and Experts for Universal Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">K</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ning</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently, unified information extraction has garnered widespread attention from the NLP community, which aims to use a unified paradigm to perform various information extraction tasks. However, prevalent unified IE approaches inevitably encounter challenges such as noise interference, abstract label semantics, and diverse span granularity. In this paper, we first present three problematic assumptions regarding the capabilities of unified information extraction model. Furthermore, we propose the General Collaborative Information Extraction (GCIE) framework to address these challenges in universal information extraction tasks. Specifically, GCIE consists of a general Recognizer as well as multiple task-specific Experts for recognizing predefined types and extracting spans respectively. The Recognizer is a large language model, while the Experts comprise a series of smaller language models. Together, they collaborate in a two-stage pipeline to perform unified information extraction. Extensive empirical experiments on 6 IE tasks and several datasets, validate the effectiveness and generality of our approach.</abstract>
<identifier type="citekey">bao-wang-2024-general</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.4</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.4/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>52</start>
<end>77</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T General Collaborative Framework between Large Language Model and Experts for Universal Information Extraction
%A Bao, K.
%A Wang, Ning
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F bao-wang-2024-general
%X Recently, unified information extraction has garnered widespread attention from the NLP community, which aims to use a unified paradigm to perform various information extraction tasks. However, prevalent unified IE approaches inevitably encounter challenges such as noise interference, abstract label semantics, and diverse span granularity. In this paper, we first present three problematic assumptions regarding the capabilities of unified information extraction model. Furthermore, we propose the General Collaborative Information Extraction (GCIE) framework to address these challenges in universal information extraction tasks. Specifically, GCIE consists of a general Recognizer as well as multiple task-specific Experts for recognizing predefined types and extracting spans respectively. The Recognizer is a large language model, while the Experts comprise a series of smaller language models. Together, they collaborate in a two-stage pipeline to perform unified information extraction. Extensive empirical experiments on 6 IE tasks and several datasets, validate the effectiveness and generality of our approach.
%R 10.18653/v1/2024.findings-emnlp.4
%U https://aclanthology.org/2024.findings-emnlp.4/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.4
%P 52-77
Markdown (Informal)
[General Collaborative Framework between Large Language Model and Experts for Universal Information Extraction](https://aclanthology.org/2024.findings-emnlp.4/) (Bao & Wang, Findings 2024)
ACL