Paper
Reasoning about In-Context Samples for Machine-Translation
Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work, we investigate how explicit reasoning can be leveraged for LLM-Based Machine Translation (MT) with in-context samples. We introduce a novel fragment-based reasoning framework in which the model first extracts parallel source-target fragments from retrieved similar ex · Authors: Maxime Bouthors, Josep Crego, François Yvon · Published 2026-08-27 · arXiv:2608.27036
- Published
- 2026-08-27
- Authors
- 3
- arXiv
- 2608.27036
- Category
- cs.CL
Abstract
arXiv:2608.27036
Maxime Bouthors, Josep Crego, François Yvon
Large Language Models (LLMs) can be trained to perform chain-of-thoughts reasoning in order to improve the reliability of their responses. In this work, we investigate how explicit reasoning can be leveraged for LLM-Based Machine Translation (MT) with in-context samples. We introduce a novel fragment-based reasoning framework in which the model first extracts parallel source-target fragments from retrieved similar exemplars, and uses these fragments as intermediate reasoning traces to produce the final translation. To train our model, we distill silver fragments and drafts from a large teacher model. Our experiments with the Qwen3 model family, over 6 languages, including up to 5 domains per language, demonstrate that fragment-based MT significantly outperforms alternative methods like standard k-shot or basic drafting.