EthioLLM: Multilingual Large Language Models for Ethiopian Languages with Task Evaluation

TL;DR

This paper introduces EthioLLM, a set of multilingual large language models for Ethiopian languages, along with a new benchmark dataset, to improve NLP capabilities for low-resource languages and evaluate their performance across multiple tasks.

Contribution

The paper presents EthioLLM models and Ethiobenchmark dataset, enabling improved NLP research and applications for Ethiopian languages, which are underrepresented in current LLM development.

Findings

Models perform competitively on downstream NLP tasks.

Open-source datasets and models facilitate further research.

Multilingual models enhance NLP for low-resource languages.

Abstract

Large language models (LLMs) have gained popularity recently due to their outstanding performance in various downstream Natural Language Processing (NLP) tasks. However, low-resource languages are still lagging behind current state-of-the-art (SOTA) developments in the field of NLP due to insufficient resources to train LLMs. Ethiopian languages exhibit remarkable linguistic diversity, encompassing a wide array of scripts, and are imbued with profound religious and cultural significance. This paper introduces EthioLLM -- multilingual large language models for five Ethiopian languages (Amharic, Ge'ez, Afan Oromo, Somali, and Tigrinya) and English, and Ethiobenchmark -- a new benchmark dataset for various downstream NLP tasks. We evaluate the performance of these models across five downstream NLP tasks. We open-source our multilingual language models, new benchmark datasets for various downstream tasks, and task-specific fine-tuned language models and discuss the performance of the models. Our dataset and models are available at the https://huggingface.co/EthioNLP repository.