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

arXiv: https://arxiv.org/abs/2310.14819 · HTML: https://mlsanity.com/paper/2310.14819/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 25 references that are in the map.
- First posted on arXiv 23 Oct 2023.

## Builds on (most cited first, 15 of 15)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [TruthfulQA: Measuring How Models Mimic Human Falsehoods](https://mlsanity.com/paper/2109.07958/) (2021)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks](https://mlsanity.com/paper/2204.07705/) (2022)
- [OpenAssistant Conversations -- Democratizing Large Language Model Alignment](https://mlsanity.com/paper/2304.07327/) (2023)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources](https://mlsanity.com/paper/2306.04751/) (2023)
- [Colossal-AI: A Unified Deep Learning System For Large-Scale Parallel Training](https://mlsanity.com/paper/2110.14883/) (2021)
- [MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation](https://mlsanity.com/paper/2211.05719/) (2022)
- [LAraBench: Benchmarking Arabic AI with Large Language Models](https://mlsanity.com/paper/2305.14982/) (2023)
- [Taqyim: Evaluating Arabic NLP Tasks Using ChatGPT Models](https://mlsanity.com/paper/2306.16322/) (2023)

## Built on by (most cited first, 7 of 7)

- [Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers](https://mlsanity.com/paper/2404.04925/) (2024)
- [Arabic Dataset for LLM Safeguard Evaluation](https://mlsanity.com/paper/2410.17040/) (2024)
- [XIFBench: Evaluating Large Language Models on Multilingual Instruction Following](https://mlsanity.com/paper/2503.07539/) (2025)
- [Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models](https://mlsanity.com/paper/2407.05502/) (2024)
- [GemmAr: Enhancing LLMs Through Arabic Instruction-Tuning](https://mlsanity.com/paper/2407.02147/) (2024)
- [Towards Inclusive NLP: Assessing Compressed Multilingual Transformers across Diverse Language Benchmarks](https://mlsanity.com/paper/2507.19699/) (2025)
- [Challenges and Recommendations for LLM-as-a-Judge in Multilingual Settings and for Low-Resource Languages](https://mlsanity.com/paper/2607.02235/) (2026)

## Abstract (arXiv)

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.