@inproceedings{gu-etal-2023-iaeval,
title = "{IAE}val: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding",
author = "Gu, Peijian and
Shen, Yaozong and
Wang, Lijie and
Wang, Quan and
Wu, Hua and
Mao, Zhendong",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.801",
doi = "10.18653/v1/2023.findings-emnlp.801",
pages = "11966--11977",
abstract = "Instance attribution (IA) aims to identify the training instances leading to the prediction of a test example, helping researchers understand the dataset better and optimize data processing. While many IA methods have been proposed recently, how to evaluate them still remains open. Previous evaluations of IA only focus on one or two dimensions and are not comprehensive. In this work, we introduce IAEval for IA methods, a systematic and comprehensive evaluation scheme covering four significant requirements: sufficiency, completeness, stability and plausibility. We elaborately design novel metrics to measure these requirements for the first time. Three representative IA methods are evaluated under IAEval on four natural language understanding datasets. Extensive experiments confirmed the effectiveness of IAEval and exhibited its ability to provide comprehensive comparison among IA methods. With IAEval, researchers can choose the most suitable IA methods for applications like model debugging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-etal-2023-iaeval">
<titleInfo>
<title>IAEval: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peijian</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaozong</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lijie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hua</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhendong</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Instance attribution (IA) aims to identify the training instances leading to the prediction of a test example, helping researchers understand the dataset better and optimize data processing. While many IA methods have been proposed recently, how to evaluate them still remains open. Previous evaluations of IA only focus on one or two dimensions and are not comprehensive. In this work, we introduce IAEval for IA methods, a systematic and comprehensive evaluation scheme covering four significant requirements: sufficiency, completeness, stability and plausibility. We elaborately design novel metrics to measure these requirements for the first time. Three representative IA methods are evaluated under IAEval on four natural language understanding datasets. Extensive experiments confirmed the effectiveness of IAEval and exhibited its ability to provide comprehensive comparison among IA methods. With IAEval, researchers can choose the most suitable IA methods for applications like model debugging.</abstract>
<identifier type="citekey">gu-etal-2023-iaeval</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.801</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.801</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>11966</start>
<end>11977</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IAEval: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding
%A Gu, Peijian
%A Shen, Yaozong
%A Wang, Lijie
%A Wang, Quan
%A Wu, Hua
%A Mao, Zhendong
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F gu-etal-2023-iaeval
%X Instance attribution (IA) aims to identify the training instances leading to the prediction of a test example, helping researchers understand the dataset better and optimize data processing. While many IA methods have been proposed recently, how to evaluate them still remains open. Previous evaluations of IA only focus on one or two dimensions and are not comprehensive. In this work, we introduce IAEval for IA methods, a systematic and comprehensive evaluation scheme covering four significant requirements: sufficiency, completeness, stability and plausibility. We elaborately design novel metrics to measure these requirements for the first time. Three representative IA methods are evaluated under IAEval on four natural language understanding datasets. Extensive experiments confirmed the effectiveness of IAEval and exhibited its ability to provide comprehensive comparison among IA methods. With IAEval, researchers can choose the most suitable IA methods for applications like model debugging.
%R 10.18653/v1/2023.findings-emnlp.801
%U https://aclanthology.org/2023.findings-emnlp.801
%U https://doi.org/10.18653/v1/2023.findings-emnlp.801
%P 11966-11977
Markdown (Informal)
[IAEval: A Comprehensive Evaluation of Instance Attribution on Natural Language Understanding](https://aclanthology.org/2023.findings-emnlp.801) (Gu et al., Findings 2023)
ACL