Macaron: Controlled, Human-Written Benchmark for Multilingual and Multicultural Reasoning via Template-Filling

Documenti analoghi

• Multicultural Spyfall: Assessing LLMs through Dynamic Multilingual Social Deduction Game
  di: Wibowo, Haryo Akbarianto, et al.
  Pubblicazione: (2026)
• The Privileged Students: On the Value of Initialization in Multilingual Knowledge Distillation
  di: Wibowo, Haryo Akbarianto, et al.
  Pubblicazione: (2024)
• Idea First, Code Later: Disentangling Problem Solving from Code Generation in Evaluating LLMs for Competitive Programming
  di: Hadhoud, Sama, et al.
  Pubblicazione: (2026)
• TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning
  di: Hudi, Frederikus, et al.
  Pubblicazione: (2025)
• COPAL-ID: Indonesian Language Reasoning with Local Culture and Nuances
  di: Wibowo, Haryo Akbarianto, et al.
  Pubblicazione: (2023)