Skip to main content
Search

Gates Foundation

1 related articles

Subscribe to updates
  1. arXiv

    Swahili math models no longer chase only the answer: Fikiria gates its reward on the reasoning trace, and its 14B model hits 79.2% on AfriMGSM

    Fikiria changes what Swahili mathematical reasoning is rewarded for: instead of scoring only the final answer, its reward multiplies a format gate by a weighted sum of exact-match accuracy and the ChrF++ similarity of the Swahili reasoning to an in-language reference chain. The two-stage recipe runs cold-start supervised fine-tuning before GRPO, and Fikiria-AfriqueQwen-14B reaches 79.2% on the AfriMGSM Swahili test set, against 68.0% for GPT-4o under the same prompt and strict scorer; in a small human evaluation, however, GPT-4o's outputs were preferred overall.

You’re all caught up