Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic

Sabri Boughorbel, Majd Hawasly


Abstract
While significant progress has been made in benchmarking Large Language Models (LLMs) across various tasks, there is a lack of comprehensive evaluation of their abilities in responding to multi-turn instructions in less-commonly tested languages like Arabic. Our paper offers a detailed examination of the proficiency of open LLMs in such scenarios in Arabic. Utilizing a customized Arabic translation of the MT-Bench benchmark suite, we employ GPT-4 as a uniform evaluator for both English and Arabic queries to assess and compare the performance of the LLMs on various open-ended tasks. Our findings reveal variations in model responses on different task categories, e.g., logic vs. literacy, when instructed in English or Arabic. We find that fine-tuned base models using multilingual and multi-turn datasets could be competitive to models trained from scratch on multilingual data. Finally, we hypothesize that an ensemble of small, open LLMs could perform competitively to proprietary LLMs on the benchmark.
Anthology ID:
2023.arabicnlp-1.11
Volume:
Proceedings of ArabicNLP 2023
Month:
December
Year:
2023
Address:
Singapore (Hybrid)
Editors:
Hassan Sawaf, Samhaa El-Beltagy, Wajdi Zaghouani, Walid Magdy, Ahmed Abdelali, Nadi Tomeh, Ibrahim Abu Farha, Nizar Habash, Salam Khalifa, Amr Keleg, Hatem Haddad, Imed Zitouni, Khalil Mrini, Rawan Almatham
Venues:
ArabicNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
128–139
Language:
URL:
https://aclanthology.org/2023.arabicnlp-1.11
DOI:
10.18653/v1/2023.arabicnlp-1.11
Bibkey:
Cite (ACL):
Sabri Boughorbel and Majd Hawasly. 2023. Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic. In Proceedings of ArabicNLP 2023, pages 128–139, Singapore (Hybrid). Association for Computational Linguistics.
Cite (Informal):
Analyzing Multilingual Competency of LLMs in Multi-Turn Instruction Following: A Case Study of Arabic (Boughorbel & Hawasly, ArabicNLP-WS 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.arabicnlp-1.11.pdf