analiza aiqbench
This research proposes a fragment-based reasoning framework that leverages explicit intermediate traces from in-context samples to enhance LLM-based machine translation. By distilling silver fragments and drafts from a teacher model, the approach significantly outperforms standard k-shot methods across multiple languages and domains using the Qwen3 architecture. The study highlights how structured reasoning over retrieved exemplars can improve translation reliability without requiring additional training data.
Reasoning about In-Context Samples for Machine-Translation
arXiv:2608.27036v1 Announce Type: new Abstract: 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.
Abstract: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.
Computation and Language (cs.CL)
arXiv:2608.27036 [cs.CL]
(or arXiv:2608.27036v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.27036 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 213 cuvinte
Subiecte conexe
Cracking the Data Science Case Study Interview
Analytics Vidhya · 26 iul. 2026
Building and evaluating model diffing agents
AI Alignment Forum · 12 iun. 2026
From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon
BAIR Blog · 29 iul. 2026
Controllable-CoT leads to covert reasoning capabilities
LessWrong · 22 sept. 2026