Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.20996 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913165130858496 |
|---|---|
| author | Belay, Tadesse Destaw Nahin, Shahriar Kabir Azime, Israel Abebe Monjur, Ocean Rei, Marek Biemann, Chris Muhammad, Shamsuddeen Hassan Yimam, Seid Muhie Chhabra, Anshuman |
| author_facet | Belay, Tadesse Destaw Nahin, Shahriar Kabir Azime, Israel Abebe Monjur, Ocean Rei, Marek Biemann, Chris Muhammad, Shamsuddeen Hassan Yimam, Seid Muhie Chhabra, Anshuman |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20996 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models Belay, Tadesse Destaw Nahin, Shahriar Kabir Azime, Israel Abebe Monjur, Ocean Rei, Marek Biemann, Chris Muhammad, Shamsuddeen Hassan Yimam, Seid Muhie Chhabra, Anshuman Computation and Language 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. |
| title | AFRILANGTUTOR: Advancing Language Tutoring and Culture Education in Low-Resource Languages with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.20996 |