GanitLLM improves Bengali math accuracy by 6-8 points over its base model by training on a difficulty-tagged corpus with Curriculum-GRPO that boosts Bengali reasoning tokens from 14% to 88%.
Lixin Wu, Na Cai, Qiao Cheng, Jiachen Wang, and Yitao Duan
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO
GanitLLM improves Bengali math accuracy by 6-8 points over its base model by training on a difficulty-tagged corpus with Curriculum-GRPO that boosts Bengali reasoning tokens from 14% to 88%.