Halwasa: Quantify and Analyze Hallucinations in Large Language Models: Arabic as a Case Study

Hamdy Mubarak, Hend Al-Khalifa, Khaloud Alkhalefah

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

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 hallucinations in LLMs can increase their reliability and usage. While hallucination is being actively studied for English and other languages, and different benchmarking datasets have been created, this area is not studied at all for Arabic. In our paper, we create the first Arabic dataset that contains 10K generated sentences by LLMs and annotate it for factuality and correctness. We provide a 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.

Original languageEnglish
Title of host publication2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings
EditorsNicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
PublisherEuropean Language Resources Association (ELRA)
Pages8008-8015
Number of pages8
ISBN (Electronic)9782493814104
Publication statusPublished - May 2024
EventJoint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024 - Hybrid, Torino, Italy
Duration: 20 May 202425 May 2024

Publication series

Name2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC-COLING 2024 - Main Conference Proceedings

Conference

ConferenceJoint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024
Country/TerritoryItaly
CityHybrid, Torino
Period20/05/2425/05/24

Fingerprint

Dive into the research topics of 'Halwasa: Quantify and Analyze Hallucinations in Large Language Models: Arabic as a Case Study'. Together they form a unique fingerprint.

Cite this