Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling
Alaa Elsetohy Mohamed bin Zayed University of Artificial Intelligence, Sama Hadhoud Mohamed bin Zayed University of Artificial Intelligence, Haryo Akbarianto Wibowo Mohamed bin Zayed University of Artificial Intelligence, Chenxi Whitehouse Meta, Genta Indra Winata Capital One, Fajri Koto Mohamed bin Zayed University of Artificial Intelligence, Alham Fikri Aji Mohamed bin Zayed University of Artificial Intelligence
原文摘要
Multilingual benchmarks rarely test reasoning over culturally grounded premises: translated datasets keep English-centric scenarios, while culture-first datasets often lack control over the reasoning required. We propose Macaron, a template-first benchmark that factorizes reasoning type and cultural aspect across question languages. Using 100 language-agnostic templates that cover 7 reasoning types, 22 cultural aspects, native annotators create scenario-aligned English and local-language multiple-choice questions, and systematically derived True/False questions. Macaron contains 11,862 instances spanning 20 countries/cultural contexts, 10 scripts, and 20 languages and dialects (including low-resource ones like Amharic, Yoruba, Zulu, Kyrgyz, and some Arabic dialects). In zero-shot evaluation of 21 multilingual LLMs, reasoning-mode models achieve the strongest performance (80.8% overall) and near-parity between English and local languages (∆MC = −1.3%), while open-weight models degrade substantially in local languages (∆MC = −6.8%) and often approach chance on T/F tasks. Culture-grounded mathematical and counting templates are consistently the hardest. The data can be accessed here https://huggingface.co/datasets/AlaaAhmed2444/Macaron.
cs.CL
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表