Luar is a reinforcement learning method enabling reasoning language models to decide when to invoke English translation for improved multilingual reasoning.
B ench MAX : A Comprehensive Multilingual Evaluation Suite for Large Language Models
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
-
Learning When to Translate for Multilingual Reasoning
Luar is a reinforcement learning method enabling reasoning language models to decide when to invoke English translation for improved multilingual reasoning.