@inproceedings{laskar-etal-2023-large,
title = "Can Large Language Models Fix Data Annotation Errors? An Empirical Study Using Debatepedia for Query-Focused Text Summarization",
author = "Laskar, Md Tahmid Rahman and
Rahman, Mizanur and
Jahan, Israt and
Hoque, Enamul and
Huang, Jimmy",
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.686",
doi = "10.18653/v1/2023.findings-emnlp.686",
pages = "10245--10255",
abstract = "Debatepedia is a publicly available dataset consisting of arguments and counter-arguments on controversial topics that has been widely used for the single-document query-focused abstractive summarization task in recent years. However, it has been recently found that this dataset is limited by noise and even most queries in this dataset do not have any relevance to the respective document. In this paper, we study whether large language models (LLMs) can be utilized to clean the Debatepedia dataset to make it suitable for query-focused abstractive summarization. More specifically, we harness the language generation capabilities of two LLMs, namely, ChatGPT and PaLM to regenerate its queries. Based on our experiments, we find that solely depending on large language models for query correction may not be very useful for data cleaning. However, we observe that leveraging a rule-based approach for data sampling followed by query regeneration using LLMs (especially ChatGPT) for the sampled instances may ensure a higher quality version of this dataset suitable for the development of more generalized query-focused text summarization models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laskar-etal-2023-large">
<titleInfo>
<title>Can Large Language Models Fix Data Annotation Errors? An Empirical Study Using Debatepedia for Query-Focused Text Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Tahmid</namePart>
<namePart type="given">Rahman</namePart>
<namePart type="family">Laskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mizanur</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Israt</namePart>
<namePart type="family">Jahan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enamul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jimmy</namePart>
<namePart type="family">Huang</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>Debatepedia is a publicly available dataset consisting of arguments and counter-arguments on controversial topics that has been widely used for the single-document query-focused abstractive summarization task in recent years. However, it has been recently found that this dataset is limited by noise and even most queries in this dataset do not have any relevance to the respective document. In this paper, we study whether large language models (LLMs) can be utilized to clean the Debatepedia dataset to make it suitable for query-focused abstractive summarization. More specifically, we harness the language generation capabilities of two LLMs, namely, ChatGPT and PaLM to regenerate its queries. Based on our experiments, we find that solely depending on large language models for query correction may not be very useful for data cleaning. However, we observe that leveraging a rule-based approach for data sampling followed by query regeneration using LLMs (especially ChatGPT) for the sampled instances may ensure a higher quality version of this dataset suitable for the development of more generalized query-focused text summarization models.</abstract>
<identifier type="citekey">laskar-etal-2023-large</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.686</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.686</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10245</start>
<end>10255</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can Large Language Models Fix Data Annotation Errors? An Empirical Study Using Debatepedia for Query-Focused Text Summarization
%A Laskar, Md Tahmid Rahman
%A Rahman, Mizanur
%A Jahan, Israt
%A Hoque, Enamul
%A Huang, Jimmy
%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 laskar-etal-2023-large
%X Debatepedia is a publicly available dataset consisting of arguments and counter-arguments on controversial topics that has been widely used for the single-document query-focused abstractive summarization task in recent years. However, it has been recently found that this dataset is limited by noise and even most queries in this dataset do not have any relevance to the respective document. In this paper, we study whether large language models (LLMs) can be utilized to clean the Debatepedia dataset to make it suitable for query-focused abstractive summarization. More specifically, we harness the language generation capabilities of two LLMs, namely, ChatGPT and PaLM to regenerate its queries. Based on our experiments, we find that solely depending on large language models for query correction may not be very useful for data cleaning. However, we observe that leveraging a rule-based approach for data sampling followed by query regeneration using LLMs (especially ChatGPT) for the sampled instances may ensure a higher quality version of this dataset suitable for the development of more generalized query-focused text summarization models.
%R 10.18653/v1/2023.findings-emnlp.686
%U https://aclanthology.org/2023.findings-emnlp.686
%U https://doi.org/10.18653/v1/2023.findings-emnlp.686
%P 10245-10255
Markdown (Informal)
[Can Large Language Models Fix Data Annotation Errors? An Empirical Study Using Debatepedia for Query-Focused Text Summarization](https://aclanthology.org/2023.findings-emnlp.686) (Laskar et al., Findings 2023)
ACL