Rethinking the Multilingual Reasoning Gap with Layer Swap
Recent reasoning Large Language Models produce a chain-of-thought (CoT) predominantly in English, even when prompted in non-English languages. Prior work suggests that forcing the CoT to remain in the input language (native reasoning) substantially degrades performance relative to allowing the model to reason in English before answering in the input language (English-pivoted reasoning). However, most studies of this native reasoning gap rely on inference-time interventions or limited native-language training data. We revisit this comparison at a larger scale and under comparable supervision. We construct long multilingual reasoning datasets across six languages (English, French, German, S...
| Authors | Maxence Lasbordes, Amélie Chatelain, Djamé Seddah |
|---|---|
| Primary category | cs.CL |
| Published | 26 May 2026 |
| Last updated at source | 26 August 2026 |
Popularity, last 3 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- lightonai/Dolci-Think-SFT-32B-MultilingualDataset · cited by
- lightonai/HumanEvalPlus_multilingualDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 19 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.