cs.CLNov 11, 2026

Show Your Work in Swahili: Reinforcement Learning for Native-Language Mathematical Reasoning

Authors: Jessica Lundin, Katherine Rosenfeld, David Adelani, Geoffrey Mosoti Nyakiongora, Halfan Ngowo, Sloan Coffin, Ralph Abboud, Guillaume Chabot-Couture

Organizations: Gates Foundation · RenPhil

Abstract

We present Fikiria, a two-stage SFT+GRPO recipe for Swahili mathematical reasoning. Its reward multiplies a format gate by a weighted sum of answer accuracy and the ChrF++ similarity of the Swahili reasoning to an in-language reference chain of thought, so that training targets the surface fidelity of the reasoning trace and not only the final answer. We train on a 2.3k-problem Swahili dataset created by translating GSM8K with GPT-4.1 and filtering with SSA-COMET. On AfriMGSM Swahili, Fikiria-AfriqueQwen-14B reaches 79.2%. Under the same fixed prompt and strict answer-format scoring, GPT-4o reaches 68.0%, partly because it often fails the required answer format; IrokoBench reports 78.8% for GPT-4o using a best-per-model prompt, a figure numerically close to ours but not directly comparable. In a small human evaluation with co-author annotators, GPT-4o's outputs were preferred overall. ChrF++ measures surface fidelity, not the validity of individual reasoning steps.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MATH-PT: A Math Reasoning Benchmark for European and Brazilian Portuguese

    Apr 1, 2026Tiago Teixeira, Ana Carolina Erthal, Juan Belieni +5Mathematical Reasoning BenchmarksMultilingual Language Model Evaluation

  2. Riazi-8B: An Urdu Large Language Model for Mathematical Reasoning

    Jun 24, 2026Azher Ali, Ibtsam Haider, Raja Khurram Shahzad +2Numerical Reasoning in Language ModelsLLM Fine-Tuning