EMNLP 2024finding0 citations
AfriInstruct: Instruction Tuning of African Languages for Diverse Tasks
Kosei Uemura, Mahe Chen, Alex Pejovic, Chika Maduabuchi, Yifei Sun, En-Shiun Annie Lee
Abstract
Large language models (LLMs) for African languages perform worse compared to their performance in high-resource languages. To address this issue, we introduce AfriInstruct, which specializes in instruction-tuning of multiple African languages covering various tasks. We trained the LLaMa-2-7B using continual pretraining and instruction fine-tuning, which demonstrates superior performance across multiple tasks. Our mixed task evaluation shows that our model outperforms GPT-3.5-Turbo and other baseline models of similar size. Our contributions fill a critical gap of LLM performance between high-resource and African languages.
BibTeX
@inproceedings{uemura-etal-2024-afriinstruct,
title = "{A}fri{I}nstruct: Instruction Tuning of {A}frican Languages for Diverse Tasks",
author = "Uemura, Kosei and
Chen, Mahe and
Pejovic, Alex and
Maduabuchi, Chika and
Sun, Yifei and
Lee, En-Shiun Annie",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.793/",
doi = "10.18653/v1/2024.findings-emnlp.793",
pages = "13571--13585"
}