Multilingual Chain-of-Thought Compression via Cross-Lingual Distillation

Abstract

Chain-of-thought reasoning improves the performance of large language models on complex tasks but often produces overly ver-bose outputs, leading to increased inference cost. This issue is exacerbated in multilingual settings, where differences in tokenization and linguistic structure result in inconsistent compression performance across languages. Existing methods are largely English-centric and tend to suffer from accuracy degradation, especially in low-resource languages. We propose M ultilingual C hain-of-thought Compression via Cross-lingual D istillation (MCD) , a unified framework that addresses these challenges through both data construction and optimization. MCD builds a cross-lingually aligned dataset using a translation-with-verification pipeline and difficulty-aware sampling, and employs a reinforcement training strategy that combines supervised fine-tuning with direct preference optimization to encourage concise yet sufficient reasoning. Experiments on multilingual mathematical benchmarks show that MCD consistently reduces reasoning length while maintaining competitive accuracy, and significantly improves robustness in low-resource languages.