New Trends for Modern Machine Translation with Large Reasoning Models

• URL: http://arxiv.org/abs/2503.10351v2
• Date: Fri, 14 Mar 2025 12:09:34 GMT
• Title: New Trends for Modern Machine Translation with Large Reasoning Models
• Authors: Sinuo Liu, Chenyang Lyu, Minghao Wu, Longyue Wang, Weihua Luo, Kaifu Zhang, Zifu Shang,
• Abstract summary: Recent advances in Large Reasoning Models (LRMs) have opened brand new possibility for Machine Translation (MT)<n>This position paper argues that LRMs substantially transformed traditional neural MT as well as LLMs-based MT paradigms.<n>We think that LRMs translation systems not merely as text converters but as multilingual cognitive agents capable of reasoning about meaning beyond the text.
• Score: 37.81295890762503
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in Large Reasoning Models (LRMs), particularly those leveraging Chain-of-Thought reasoning (CoT), have opened brand new possibility for Machine Translation (MT). This position paper argues that LRMs substantially transformed traditional neural MT as well as LLMs-based MT paradigms by reframing translation as a dynamic reasoning task that requires contextual, cultural, and linguistic understanding and reasoning. We identify three foundational shifts: 1) contextual coherence, where LRMs resolve ambiguities and preserve discourse structure through explicit reasoning over cross-sentence and complex context or even lack of context; 2) cultural intentionality, enabling models to adapt outputs by inferring speaker intent, audience expectations, and socio-linguistic norms; 3) self-reflection, LRMs can perform self-reflection during the inference time to correct the potential errors in translation especially extremely noisy cases, showing better robustness compared to simply mapping X->Y translation. We explore various scenarios in translation including stylized translation, document-level translation and multimodal translation by showcasing empirical examples that demonstrate the superiority of LRMs in translation. We also identify several interesting phenomenons for LRMs for MT including auto-pivot translation as well as the critical challenges such as over-localisation in translation and inference efficiency. In conclusion, we think that LRMs redefine translation systems not merely as text converters but as multilingual cognitive agents capable of reasoning about meaning beyond the text. This paradigm shift reminds us to think of problems in translation beyond traditional translation scenarios in a much broader context with LRMs - what we can achieve on top of it.

Related papers

• How Well Do Large Reasoning Models Translate? A Comprehensive Evaluation for Multi-Domain Machine Translation [11.5400003750047]
  Large language models (LLMs) have demonstrated strong performance in general-purpose machine translation.<n>Recent advancements in LRMs, raise the question of whether structured reasoning can enhance translation quality across diverse domains.
  arXiv  Detail & Related papers  (2025-05-26T13:43:37Z)
• Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation [33.08089616645845]
  The advent of Large Language Models (LLMs) has significantly reshaped the landscape of machine translation (MT) We analyze techniques such as few-shot prompting, cross-lingual transfer, and parameter-efficient fine-tuning that enable effective adaptation to under-resourced settings. We discuss persistent challenges such as hallucinations, evaluation inconsistencies, and inherited biases while also evaluating emerging LLM-driven metrics for translation quality.
  arXiv  Detail & Related papers  (2025-04-02T17:26:40Z)
• R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning [23.721573333602677]
  This paper introduces R1-Translator (R1-T1), a novel framework to achieve inference-time reasoning for general machine translation (MT) via reinforcement learning (RL)<n>Our approach pioneers three innovations: (1) extending reasoning-based translation beyond MT sub-tasks to six languages and diverse tasks (e.g., legal/medical domain adaptation, idiom resolution); and (2) formalizing six expert-curated CoT templates that mirror hybrid human strategies like context-aware paraphrasing and back translation.<n> Experimental results indicate a steady translation performance improvement in 11 languages and 40 translation directions on Flores-101 test set, especially on the
  arXiv  Detail & Related papers  (2025-02-27T03:57:00Z)
• Refining Translations with LLMs: A Constraint-Aware Iterative Prompting Approach [7.5069214839655345]
  Large language models (LLMs) have demonstrated remarkable proficiency in machine translation (MT) We propose a multi-step prompt chain that enhances translation faithfulness by prioritizing key terms crucial for semantic accuracy. Experiments using Llama and Qwen as base models on the FLORES-200 and WMT datasets demonstrate significant improvements over baselines.
  arXiv  Detail & Related papers  (2024-11-13T05:40:24Z)
• LLM-based Translation Inference with Iterative Bilingual Understanding [52.46978502902928]
  We propose a novel Iterative Bilingual Understanding Translation method based on the cross-lingual capabilities of large language models (LLMs) The cross-lingual capability of LLMs enables the generation of contextual understanding for both the source and target languages separately. The proposed IBUT outperforms several strong comparison methods.
  arXiv  Detail & Related papers  (2024-10-16T13:21:46Z)
• MT-PATCHER: Selective and Extendable Knowledge Distillation from Large Language Models for Machine Translation [61.65537912700187]
  Large Language Models (LLM) have demonstrated their strong ability in the field of machine translation (MT) We propose a framework called MT-Patcher, which transfers knowledge from LLMs to existing MT models in a selective, comprehensive and proactive manner.
  arXiv  Detail & Related papers  (2024-03-14T16:07:39Z)
• TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement [26.26493253161022]
  Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT) We introduce a systematic LLM-based self-refinement translation framework, named textbfTEaR.
  arXiv  Detail & Related papers  (2024-02-26T07:58:12Z)
• Towards Effective Disambiguation for Machine Translation with Large Language Models [65.80775710657672]
  We study the capabilities of large language models to translate "ambiguous sentences" Experiments show that our methods can match or outperform state-of-the-art systems such as DeepL and NLLB in four out of five language directions.
  arXiv  Detail & Related papers  (2023-09-20T22:22:52Z)
• Adaptive Machine Translation with Large Language Models [7.803471587734353]
  We investigate how we can utilize in-context learning to improve real-time adaptive machine translation. We conduct experiments across five diverse language pairs, namely English-to-Arabic (EN-AR), English-to-Chinese (EN-ZH), English-to-French (EN-FR), English-to-Kinyarwanda (EN-RW), and English-to-Spanish (EN-ES)
  arXiv  Detail & Related papers  (2023-01-30T21:17:15Z)
• Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation [72.6667341525552]
  We present a new MMT approach based on a strong text-only MT model, which uses neural adapters and a novel guided self-attention mechanism. We also introduce CoMMuTE, a Contrastive Multimodal Translation Evaluation set of ambiguous sentences and their possible translations. Our approach obtains competitive results compared to strong text-only models on standard English-to-French, English-to-German and English-to-Czech benchmarks.
  arXiv  Detail & Related papers  (2022-12-20T10:18:18Z)
• When Does Translation Require Context? A Data-driven, Multilingual Exploration [71.43817945875433]
  proper handling of discourse significantly contributes to the quality of machine translation (MT) Recent works in context-aware MT attempt to target a small set of discourse phenomena during evaluation. We develop the Multilingual Discourse-Aware benchmark, a series of taggers that identify and evaluate model performance on discourse phenomena.
  arXiv  Detail & Related papers  (2021-09-15T17:29:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.