AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models

TL;DR

This paper introduces AFRILANGTUTOR, a multilingual language tutoring model for African languages, built using a large dataset of dictionary entries and training data, demonstrating improved performance over base models.

Contribution

The paper presents a new dataset and training approach for low-resource African languages, enabling effective fine-tuning of large language models for language tutoring.

Findings

Models trained on AFRILANGTUTOR outperform base models.

Combining SFT and DPO yields significant performance gains.

Resources are publicly available at Hugging Face.

Abstract

How can language learning systems be developed for languages that lack sufficient training resources? This challenge is increasingly faced by developers across the African continent who aim to build AI systems capable of understanding and responding in local languages. To address this gap, we introduce AFRILANGDICT, a collection of 194.7K African language-English dictionary entries designed as seed resources for generating language-learning materials, enabling us to automatically construct large-scale, diverse, and verifiable student-tutor question-answer interactions suitable for training AI-assisted language tutors. Using AFRILANGDICT, we build AFRILANGEDU, a dataset of 78.9K multi-turn training examples for Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO). Using AFRILANGEDU, we train language tutoring models collectively referred to as AFRILANGTUTOR. We fine-tune two multilingual LLMs: Llama-3-8B-IT and Gemma-3-12B-IT on AFRILANGEDU across 10 African languages and evaluate their performance. Our results show that models trained on AFRILANGEDU consistently outperform their base counterparts, and combining SFT and DPO yields substantial improvements, with gains ranging from 1.8% to 15.5% under LLM-as-a-judge evaluations across four criteria. To facilitate further research on low-resource languages -- all resources are available at https://huggingface.co/afrilang-edu.