@inproceedings{zhang-etal-2024-unexpected,
title = "Unexpected Phenomenon: {LLM}s{'} Spurious Associations in Information Extraction",
author = "Zhang, Weiyan and
Lu, Wanpeng and
Wang, Jiacheng and
Wang, Yating and
Chen, Lihan and
Jiang, Haiyun and
Liu, Jingping and
Ruan, Tong",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.545",
pages = "9176--9190",
abstract = "Information extraction plays a critical role in natural language processing. When applying large language models (LLMs) to this domain, we discover an unexpected phenomenon: LLMs{'} spurious associations. In tasks such as relation extraction, LLMs can accurately identify entity pairs, even if the given relation (label) is semantically unrelated to the pre-defined original one. To find these labels, we design two strategies in this study, including forward label extension and backward label validation. We also leverage the extended labels to improve model performance. Our comprehensive experiments show that spurious associations occur consistently in both Chinese and English datasets across various LLM sizes. Moreover, the use of extended labels significantly enhances LLM performance in information extraction tasks. Remarkably, there is a performance increase of 9.55{\%}, 11.42{\%}, and 21.27{\%} in F1 scores on the SciERC, ACE05, and DuEE datasets, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2024-unexpected">
<titleInfo>
<title>Unexpected Phenomenon: LLMs’ Spurious Associations in Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weiyan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanpeng</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiacheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yating</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lihan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haiyun</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingping</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Information extraction plays a critical role in natural language processing. When applying large language models (LLMs) to this domain, we discover an unexpected phenomenon: LLMs’ spurious associations. In tasks such as relation extraction, LLMs can accurately identify entity pairs, even if the given relation (label) is semantically unrelated to the pre-defined original one. To find these labels, we design two strategies in this study, including forward label extension and backward label validation. We also leverage the extended labels to improve model performance. Our comprehensive experiments show that spurious associations occur consistently in both Chinese and English datasets across various LLM sizes. Moreover, the use of extended labels significantly enhances LLM performance in information extraction tasks. Remarkably, there is a performance increase of 9.55%, 11.42%, and 21.27% in F1 scores on the SciERC, ACE05, and DuEE datasets, respectively.</abstract>
<identifier type="citekey">zhang-etal-2024-unexpected</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.545</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>9176</start>
<end>9190</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Unexpected Phenomenon: LLMs’ Spurious Associations in Information Extraction
%A Zhang, Weiyan
%A Lu, Wanpeng
%A Wang, Jiacheng
%A Wang, Yating
%A Chen, Lihan
%A Jiang, Haiyun
%A Liu, Jingping
%A Ruan, Tong
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F zhang-etal-2024-unexpected
%X Information extraction plays a critical role in natural language processing. When applying large language models (LLMs) to this domain, we discover an unexpected phenomenon: LLMs’ spurious associations. In tasks such as relation extraction, LLMs can accurately identify entity pairs, even if the given relation (label) is semantically unrelated to the pre-defined original one. To find these labels, we design two strategies in this study, including forward label extension and backward label validation. We also leverage the extended labels to improve model performance. Our comprehensive experiments show that spurious associations occur consistently in both Chinese and English datasets across various LLM sizes. Moreover, the use of extended labels significantly enhances LLM performance in information extraction tasks. Remarkably, there is a performance increase of 9.55%, 11.42%, and 21.27% in F1 scores on the SciERC, ACE05, and DuEE datasets, respectively.
%U https://aclanthology.org/2024.findings-acl.545
%P 9176-9190
Markdown (Informal)
[Unexpected Phenomenon: LLMs’ Spurious Associations in Information Extraction](https://aclanthology.org/2024.findings-acl.545) (Zhang et al., Findings 2024)
ACL
- Weiyan Zhang, Wanpeng Lu, Jiacheng Wang, Yating Wang, Lihan Chen, Haiyun Jiang, Jingping Liu, and Tong Ruan. 2024. Unexpected Phenomenon: LLMs’ Spurious Associations in Information Extraction. In Findings of the Association for Computational Linguistics ACL 2024, pages 9176–9190, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.