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

2026-04-22

AI Summary

This study addresses the challenge of building effective AI language learning systems for low-resource African languages, which suffer from a scarcity of high-quality training data. To this end, the authors propose a data generation approach leveraging AFRILANGDICT, a newly constructed dictionary covering ten African languages aligned with English, to create AFRILANGEDU—a scalable and verifiable multi-turn question-answering educational dataset. Using this dataset, they train AI language tutoring models on multilingual large language models such as Llama-3-8B-IT and Gemma-2-9B-IT through supervised fine-tuning (SFT) combined with direct preference optimization (DPO). Experimental results demonstrate that the proposed method significantly outperforms baseline approaches across four automatic evaluation metrics, with the joint SFT and DPO training yielding performance gains ranging from 1.8% to 15.5%.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Learning Human Values and Preferences

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• low-resource languages
• language tutoring
• African languages
• language learning systems
• culture education

Innovation

• low-resource languages
• language tutoring
• dictionary-based data generation
• supervised fine-tuning
• direct preference optimization