Search papers, labs, and topics across Lattice.
This paper explores the application of explicit reasoning in large language models for machine translation by introducing a fragment-based reasoning framework. By extracting parallel source-target fragments from similar exemplars, the model utilizes these fragments as intermediate reasoning traces to enhance translation accuracy. Experiments with the Qwen3 model family across six languages and multiple domains reveal that this fragment-based approach significantly outperforms traditional k-shot and basic drafting methods.
Fragment-based reasoning in machine translation could redefine how LLMs leverage in-context samples for improved accuracy and reliability.
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.
