Reasoning about In-Context Samples for Machine-Translation
On the map: LLM reasoning → Reasoning benchmarks and evaluation
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 16 of its 63 references that are in the map. First posted on arXiv 27 Aug 2026.
Builds on
16 of 63 references.
Closest ancestors · 6
Same direction, newest first
- 2026Unlocking Reasoning Capability on Machine Translation in Large Language Models16 Feb
- 2025LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens13 Oct
- 2025Qwen3 Technical Report14 May
- 2025MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learning14 Apr
- 2025R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning27 Feb
- 2025Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis17 Feb
Other references · 10
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2021Training Verifiers to Solve Math Word Problemscited by 10,109
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
- 2023How Good Are GPT Models at Machine Translation? A Comprehensive Evaluationcited by 348
- 2024Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoningcited by 279
- 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 145
- 2024TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinementcited by 39
- 2022Nearest Neighbor Non-autoregressive Text Generationcited by 7
- 2023OpusCleaner and OpusTrainer, open source toolkits for training Machine Translation and Large language modelscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025New Trends for Modern Machine Translation with Large Reasoning Models
- 2025How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation
- 2025Chain-of-Thought Reasoning Improves Context-Aware Translation with Large Language Models
- 2026Reasoning over Grammar: Can Synthetic Linguistic Reasoning Traces Enhance Low-Resource Machine Translation?
- 2026When Does Reasoning Help in Machine Translation? A Hierarchical Analysis of LRM Reasoning Traces
- 2025Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMs
- 2025Test-Time Scaling of Reasoning Models for Machine Translation
- 2024MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation