Kosei Uemura

kosei.uemura@mila.quebec

Research Intern - McGill University

Supervisor

David Ifeoluwa Adelani

Research Topics

Computer Vision

Generative Models

Natural Language Processing

GitHub

Publications

MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation

Tianyi Xu

Kosei Uemura

Alfred Malengo Kondoro

Tadesse Destaw Belay

Catherine Nana Nyaah Essuman

Ifeoma Okoh

Ganiyat Afolabi

Ayodele Awokoya

David Ifeoluwa Adelani

Large language models have made substantial progress in mathematical reasoning. However, benchmark development for multilingual evaluation h… (see more)as lagged behind English in both difficulty and recency. Recently, GSM-Symbolic showed a strong evidence of high variance when models are evaluated on different instantiations of the same question; however, the evaluation was conducted only in English. In this paper, we introduce MGSM-Pro, an extension of MGSM dataset with GSM-Symbolic approach. Our dataset provides five instantiations per MGSM question by varying names, digits and irrelevant context. Evaluations across nine languages reveal that many low-resource languages suffer large performance drops when tested on digit instantiations different from those in the original test set. We further find that models robustness in HRL setting do not necessarily translate to LRL. Moreover, proprietary models, such as Gemini 2.5 Flash and GPT-4.1 are less robust to digit, whereas Gemini 3.0 Pro is more robust. Among open models, GPT-OSS 120B and DeepSeek v3 show stronger robustness. Based on these findings, we recommend evaluating each problem using at least five digit-varying instantiations to obtain a more robust and realistic assessment of math reasoning.

2026-01-28

arXiv (preprint)

doi.org

arxiv.org

AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages

Kosei Uemura

Miaoran Zhang

David Ifeoluwa Adelani

2025-10-26

ArXiv (preprint)

doi.org

arxiv.org