@inproceedings{mubarak-etal-2024-halwasa-quantify,
title = "Halwasa: Quantify and Analyze Hallucinations in Large Language Models: {A}rabic as a Case Study",
author = "Mubarak, Hamdy and
Al-Khalifa, Hend and
Alkhalefah, Khaloud Suliman",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.705",
pages = "8008--8015",
abstract = "Large Language Models (LLMs) have shown superb abilities to generate texts that are indistinguishable from human-generated texts in many cases. However, sometimes they generate false, incorrect, or misleading content, which is often described as {``}hallucinations{''}. Quantifying and analyzing hallucination in LLMs can increase their reliability and usage. While hallucination is being actively studied for English and other languages, and different benchmarking datsets have been created, this area is not studied at all for Arabic. In our paper, we create the first Arabic dataset that contains 10K of generated sentences by LLMs and annotate it for factuality and correctness. We provide detailed analysis of the dataset to analyze factual and linguistic errors. We found that 25{\%} of the generated sentences are factually incorrect. We share the dataset with the research community.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mubarak-etal-2024-halwasa-quantify">
<titleInfo>
<title>Halwasa: Quantify and Analyze Hallucinations in Large Language Models: Arabic as a Case Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hamdy</namePart>
<namePart type="family">Mubarak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khaloud</namePart>
<namePart type="given">Suliman</namePart>
<namePart type="family">Alkhalefah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large Language Models (LLMs) have shown superb abilities to generate texts that are indistinguishable from human-generated texts in many cases. However, sometimes they generate false, incorrect, or misleading content, which is often described as “hallucinations”. Quantifying and analyzing hallucination in LLMs can increase their reliability and usage. While hallucination is being actively studied for English and other languages, and different benchmarking datsets have been created, this area is not studied at all for Arabic. In our paper, we create the first Arabic dataset that contains 10K of generated sentences by LLMs and annotate it for factuality and correctness. We provide detailed analysis of the dataset to analyze factual and linguistic errors. We found that 25% of the generated sentences are factually incorrect. We share the dataset with the research community.</abstract>
<identifier type="citekey">mubarak-etal-2024-halwasa-quantify</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.705</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8008</start>
<end>8015</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Halwasa: Quantify and Analyze Hallucinations in Large Language Models: Arabic as a Case Study
%A Mubarak, Hamdy
%A Al-Khalifa, Hend
%A Alkhalefah, Khaloud Suliman
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F mubarak-etal-2024-halwasa-quantify
%X Large Language Models (LLMs) have shown superb abilities to generate texts that are indistinguishable from human-generated texts in many cases. However, sometimes they generate false, incorrect, or misleading content, which is often described as “hallucinations”. Quantifying and analyzing hallucination in LLMs can increase their reliability and usage. While hallucination is being actively studied for English and other languages, and different benchmarking datsets have been created, this area is not studied at all for Arabic. In our paper, we create the first Arabic dataset that contains 10K of generated sentences by LLMs and annotate it for factuality and correctness. We provide detailed analysis of the dataset to analyze factual and linguistic errors. We found that 25% of the generated sentences are factually incorrect. We share the dataset with the research community.
%U https://aclanthology.org/2024.lrec-main.705
%P 8008-8015
Markdown (Informal)
[Halwasa: Quantify and Analyze Hallucinations in Large Language Models: Arabic as a Case Study](https://aclanthology.org/2024.lrec-main.705) (Mubarak et al., LREC-COLING 2024)
ACL