Is continuous CoT better suited for multilingual reasoning?

Ali Hamza Bashir, Behzad Shomali, Markus Frey, Mehdi Ali, Rafet Sifa, David Berghaus

Track: tiny / short paper (up to 5 pages)

Keywords: Continuous CoT, latent reasoning, multilingual reasoning, cross-lingual generalization, low-resource languages

Abstract: We investigate whether performing reasoning in a continuous latent space leads to more robust multilingual capabilities. We compare Continuous Chain-of-Thought (using the CODI framework) against standard supervised fine-tuning across five typologically diverse languages: English, Chinese, German, French, and Urdu. Our experiments on GSM8k and CommonsenseQA demonstrate that continuous reasoning significantly outperforms explicit reasoning on low-resource languages, particularly in zero-shot settings where the target language was not seen during training. Additionally, this approach achieves extreme efficiency, compressing reasoning traces by approximately $29\times$ to $50\times$. These findings indicate that continuous latent representations naturally exhibit greater language invariance, offering a scalable solution for cross-lingual reasoning.

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Submission Number: 38