Year: 2026
Type: conference-paper
Abstract: Chain-of-thought reasoning improves the performance of large language models on complex tasks but often produces overly verbose 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 Englishcentric and tend to suffer from accuracy degradation, especially in low-resource languages.We propose Multilingual Chain-of-thought Compression via Cross-lingual Distillation (MCD), a unified framework that addresses these challenges through both data construction and optimization.MCD builds a crosslingually aligned dataset using a translationwith-verification pipeline and difficulty-aware sampling, and employs a reinforcement training strategy that combines supervised finetuning 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.
Authors: Jiarui Wan, Songming Zhang, Yufeng Chen
Institution: Beijing Jiaotong University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166873905