Improving Multilingual Math Reasoning for African Languages
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912395243290624 |
|---|---|
| author | Ogundepo, Odunayo Oladipo, Akintunde Ogueji, Kelechi Adenuga, Esther Adelani, David Ifeoluwa Lin, Jimmy |
| author_facet | Ogundepo, Odunayo Oladipo, Akintunde Ogueji, Kelechi Adenuga, Esther Adelani, David Ifeoluwa Lin, Jimmy |
| contents | Researchers working on low-resource languages face persistent challenges due to limited data availability and restricted access to computational resources. Although most large language models (LLMs) are predominantly trained in high-resource languages, adapting them to low-resource contexts, particularly African languages, requires specialized techniques. Several strategies have emerged for adapting models to low-resource languages in todays LLM landscape, defined by multi-stage pre-training and post-training paradigms. However, the most effective approaches remain uncertain. This work systematically investigates which adaptation strategies yield the best performance when extending existing LLMs to African languages. We conduct extensive experiments and ablation studies to evaluate different combinations of data types (translated versus synthetically generated), training stages (pre-training versus post-training), and other model adaptation configurations. Our experiments focuses on mathematical reasoning tasks, using the Llama 3.1 model family as our base model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19848 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Multilingual Math Reasoning for African Languages Ogundepo, Odunayo Oladipo, Akintunde Ogueji, Kelechi Adenuga, Esther Adelani, David Ifeoluwa Lin, Jimmy Computation and Language Researchers working on low-resource languages face persistent challenges due to limited data availability and restricted access to computational resources. Although most large language models (LLMs) are predominantly trained in high-resource languages, adapting them to low-resource contexts, particularly African languages, requires specialized techniques. Several strategies have emerged for adapting models to low-resource languages in todays LLM landscape, defined by multi-stage pre-training and post-training paradigms. However, the most effective approaches remain uncertain. This work systematically investigates which adaptation strategies yield the best performance when extending existing LLMs to African languages. We conduct extensive experiments and ablation studies to evaluate different combinations of data types (translated versus synthetically generated), training stages (pre-training versus post-training), and other model adaptation configurations. Our experiments focuses on mathematical reasoning tasks, using the Llama 3.1 model family as our base model. |
| title | Improving Multilingual Math Reasoning for African Languages |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2505.19848 |