@inproceedings{chen-etal-2024-double,
title = "Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition",
author = "Chen, Wei and
Zhao, Lili and
Zheng, Zhi and
Xu, Tong and
Wang, Yang and
Chen, Enhong",
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.180/",
doi = "10.18653/v1/2024.findings-emnlp.180",
pages = "3172--3181",
abstract = "Recently, few-shot Named Entity Recognition (NER) has attracted significant attention due to the high cost of obtaining high-quality labeled data. Decomposition-based methods have demonstrated remarkable performance on this task, which initially train a type-independent span detector and subsequently classify the detected spans based on their types. However, this framework has an evident drawback as a domain-agnostic detector cannot ensure the identification of only those entity spans that are specific to the target domain. To address this issue, we propose Double-Checker, which leverages collaboration between Large Language Models (LLMs) and small models. Specifically, we employ LLMs to verify candidate spans predicted by the small model and eliminate any spans that fall outside the scope of the target domain. Extensive experiments validate the effectiveness of our method, consistently yielding improvements over two baseline approaches. Our code is available at https://github.com/fanshu6hao/Double-Checker."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2024-double">
<titleInfo>
<title>Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lili</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enhong</namePart>
<namePart type="family">Chen</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, few-shot Named Entity Recognition (NER) has attracted significant attention due to the high cost of obtaining high-quality labeled data. Decomposition-based methods have demonstrated remarkable performance on this task, which initially train a type-independent span detector and subsequently classify the detected spans based on their types. However, this framework has an evident drawback as a domain-agnostic detector cannot ensure the identification of only those entity spans that are specific to the target domain. To address this issue, we propose Double-Checker, which leverages collaboration between Large Language Models (LLMs) and small models. Specifically, we employ LLMs to verify candidate spans predicted by the small model and eliminate any spans that fall outside the scope of the target domain. Extensive experiments validate the effectiveness of our method, consistently yielding improvements over two baseline approaches. Our code is available at https://github.com/fanshu6hao/Double-Checker.</abstract>
<identifier type="citekey">chen-etal-2024-double</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.180</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.180/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>3172</start>
<end>3181</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition
%A Chen, Wei
%A Zhao, Lili
%A Zheng, Zhi
%A Xu, Tong
%A Wang, Yang
%A Chen, Enhong
%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 chen-etal-2024-double
%X Recently, few-shot Named Entity Recognition (NER) has attracted significant attention due to the high cost of obtaining high-quality labeled data. Decomposition-based methods have demonstrated remarkable performance on this task, which initially train a type-independent span detector and subsequently classify the detected spans based on their types. However, this framework has an evident drawback as a domain-agnostic detector cannot ensure the identification of only those entity spans that are specific to the target domain. To address this issue, we propose Double-Checker, which leverages collaboration between Large Language Models (LLMs) and small models. Specifically, we employ LLMs to verify candidate spans predicted by the small model and eliminate any spans that fall outside the scope of the target domain. Extensive experiments validate the effectiveness of our method, consistently yielding improvements over two baseline approaches. Our code is available at https://github.com/fanshu6hao/Double-Checker.
%R 10.18653/v1/2024.findings-emnlp.180
%U https://aclanthology.org/2024.findings-emnlp.180/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.180
%P 3172-3181
Markdown (Informal)
[Double-Checker: Large Language Model as a Checker for Few-shot Named Entity Recognition](https://aclanthology.org/2024.findings-emnlp.180/) (Chen et al., Findings 2024)
ACL