Jul 2026· Annual Meeting of the Association for Computational Linguistics· pp. 30339-30370· 0 citations· 44 references
Computer Science
TL;DR
TwT (Translation with Thought), a resource-rational framework that learns to modulate inference between intuitive and deliberate reasoning, confirms that aligning translation behavior with cognitive principles enables robust generalization, high translation quality, and efficient reasoning in MDMT.
Abstract
Multi-domain machine translation (MDMT) poses a unique challenge due to varying levels of linguistic complexity across domains. Inspired by human translators'ability to adapt reasoning effort based on difficulty, we propose TwT (Translation with Thought), a resource-rational framework that learns to modulate inference between intuitive and deliberate reasoning. TwT is trained in two stages: (1) supervised fine-tuning on difficulty-aware long chain-of-thought traces distilled from DeepSeek-R1 and rewritten by GPT-4o to reflect human-like reasoning economy, and (2) reinforcement learning with a hybrid reward to optimize translation quality and reasoning efficiency. Evaluated on 15 benchmarks spanning in-domain and out-of-domain settings, as well as 3 seen and 59 unseen languages, with ablations across three backbone models, TwT-7B and TwT-14B outperform much larger SOTA reasoning models in translation quality, while reducing token usage by 32--60\%. These results confirm that aligning translation behavior with cognitive principles enables robust generalization, high translation quality, and efficient reasoning in MDMT.
PAMT is proposed, a process-aligned training framework that combines cold-start domain-aware Long-CoT supervision with reinforcement learning that improves over base models, outperforms MT-specialized baselines on average, and remains competitive with strong LLMs/LRMs across in-domain, OOD, and multilingual settings.
Yongshi Ye, Biao Fu, Chongxuan Huang et al.· 0 citations
The results show that the quality of small ``base'' models can be greatly enhanced, and that reinforcement learning with verifiable rewards can be applied to NMT in the legal domain and surpasses the translation quality of supervised fine-tuning.
Aixiu An, Michael Jungo, Eloi Eynard et al.· 0 citations
Reinforcement learning with verifiable rewards (RLVR) has been established as a viable paradigm for the post-training of Large Language Models (LLMs), including downstream tasks, such as Neural Machine Translation (NMT). With the latest research indicating that RLVR could be the preferred training method for translating legal documents due to the induced reasoning capabilities, it raises the question whether it is really attributed to the reasoning or more generally to the training paradigm. We investigate the importance of including the model's reasoning trace in the generated responses during both training and inference by systematically omitting it from one of the phases. Our experiments show that including the reasoning, specifically during inference, has a positive effect on the overall translation quality. Furthermore, we recognise that the reasoning leads to an increase in output tokens, hence we study the cost-quality tradeoff between the increased computational demands and the improved translation quality.
Michael Jungo, Aixiu An· Proceedings of the 2026 ACM...· 0 citations
LatentMT is introduced, the first systematic study of latent-reasoning LoopLMs for machine translation that adapts a small 2.6B-parameter backbone model with lightweight training and shows that hidden-representation differences shrink along the recurrent reasoning-step axis, supporting the observed saturation in performance.
Wei-Rui Chen, Samar M. Magdy, Chiyu Zhang et al.· 0 citations
A novel fragment-based reasoning framework is introduced 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.
Maxime Bouthors, J. Crego, François Yvon· 0 citations
The Onramp-Sequence Cross-Distillation (OSCD) is introduced, a post-training algorithm that projects high-resource reasoning trajectories into low-resource vocabulary subspaces during generative training rollouts via an integrated translator agentic loop, ensuring the stable and efficient translation of dynamically generated reference samples for fine-tuning.
Sean Gip Lim, William-Chandra Tjhi, Hai Leong Chieu· 0 citations
