@inproceedings{fatahi-bayat-etal-2023-fleek,
title = "{FLEEK}: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge",
author = "Fatahi Bayat, Farima and
Qian, Kun and
Han, Benjamin and
Sang, Yisi and
Belyy, Anton and
Khorshidi, Samira and
Wu, Fei and
Ilyas, Ihab and
Li, Yunyao",
editor = "Feng, Yansong and
Lefever, Els",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-demo.10",
doi = "10.18653/v1/2023.emnlp-demo.10",
pages = "124--130",
abstract = "Detecting factual errors of textual information, whether generated by large language models (LLM) or curated by humans, is crucial for making informed decisions. LLMs{'} inability to attribute their claims to external knowledge and their tendency to hallucinate makes it difficult to rely on their responses. Humans, too, are prone to factual errors in their writing. Since manual detection and correction of factual er- rors is labor-intensive, developing an automatic approach can greatly reduce human effort. We present a prototype tool that automatically extracts factual claims from text, gathers evidence from external knowledge sources, evaluates the factuality of each claim, and suggests revisions for identified errors using the collected evidence. Initial empirical evaluation on fact error detection (77-85{\%} F1) shows the potential of our tool.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fatahi-bayat-etal-2023-fleek">
<titleInfo>
<title>FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Farima</namePart>
<namePart type="family">Fatahi Bayat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yisi</namePart>
<namePart type="family">Sang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anton</namePart>
<namePart type="family">Belyy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samira</namePart>
<namePart type="family">Khorshidi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ihab</namePart>
<namePart type="family">Ilyas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</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>Detecting factual errors of textual information, whether generated by large language models (LLM) or curated by humans, is crucial for making informed decisions. LLMs’ inability to attribute their claims to external knowledge and their tendency to hallucinate makes it difficult to rely on their responses. Humans, too, are prone to factual errors in their writing. Since manual detection and correction of factual er- rors is labor-intensive, developing an automatic approach can greatly reduce human effort. We present a prototype tool that automatically extracts factual claims from text, gathers evidence from external knowledge sources, evaluates the factuality of each claim, and suggests revisions for identified errors using the collected evidence. Initial empirical evaluation on fact error detection (77-85% F1) shows the potential of our tool.</abstract>
<identifier type="citekey">fatahi-bayat-etal-2023-fleek</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-demo.10</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-demo.10</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>124</start>
<end>130</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge
%A Fatahi Bayat, Farima
%A Qian, Kun
%A Han, Benjamin
%A Sang, Yisi
%A Belyy, Anton
%A Khorshidi, Samira
%A Wu, Fei
%A Ilyas, Ihab
%A Li, Yunyao
%Y Feng, Yansong
%Y Lefever, Els
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F fatahi-bayat-etal-2023-fleek
%X Detecting factual errors of textual information, whether generated by large language models (LLM) or curated by humans, is crucial for making informed decisions. LLMs’ inability to attribute their claims to external knowledge and their tendency to hallucinate makes it difficult to rely on their responses. Humans, too, are prone to factual errors in their writing. Since manual detection and correction of factual er- rors is labor-intensive, developing an automatic approach can greatly reduce human effort. We present a prototype tool that automatically extracts factual claims from text, gathers evidence from external knowledge sources, evaluates the factuality of each claim, and suggests revisions for identified errors using the collected evidence. Initial empirical evaluation on fact error detection (77-85% F1) shows the potential of our tool.
%R 10.18653/v1/2023.emnlp-demo.10
%U https://aclanthology.org/2023.emnlp-demo.10
%U https://doi.org/10.18653/v1/2023.emnlp-demo.10
%P 124-130
Markdown (Informal)
[FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge](https://aclanthology.org/2023.emnlp-demo.10) (Fatahi Bayat et al., EMNLP 2023)
ACL
- Farima Fatahi Bayat, Kun Qian, Benjamin Han, Yisi Sang, Anton Belyy, Samira Khorshidi, Fei Wu, Ihab Ilyas, and Yunyao Li. 2023. FLEEK: Factual Error Detection and Correction with Evidence Retrieved from External Knowledge. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 124–130, Singapore. Association for Computational Linguistics.