R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning

Minggui He, Yilun Liu, Shimin Tao, Hongyong Zeng, Jian Zhang, Yuanchang Luo, Li Zhang, Daimeng Wei, Weibin Meng, Osamu Yoshie


Abstract
Despite recent breakthroughs in reasoning-enhanced large language models (LLMs), incorporating inference-time reasoning into application tasks such as machine translation (MT), where human translators naturally employ structured, multi-layered reasoning chain-of-thoughts (CoTs), is yet un-derexplored. Existing methods either design a fixed CoT tailored for a specific MT sub-task (e.g., literature translation), or rely on synthesizing CoTs unaligned with humans and supervised fine-tuning (SFT) prone to overfitting, limiting their adaptability to diverse translation scenarios. This paper introduces R1-Translator (R1-T1), a novel framework to achieve inference-time reasoning for general MT via reinforcement learning (RL) with human-aligned CoTs comprising six common patterns. Our approach pioneers three innovations: (1) verifying reasoning-based translation in various MT scenarios (e.g., multilingual MT, domain MT) unseen from the training phase; (2) formalizing six expert-curated CoT templates that mirror hybrid human strategies like context-aware paraphrasing and round-trip translation; and (3) enabling more flexible CoTs through an RL stage after cold-start. Both human and automatic evaluation results indicate a steady translation quality improvement in a total of 10+ languages and 40+ translation directions on Flores-101 test set and four domain-specific MT tasks, especially on the languages unseen from training.
Anthology ID:
2026.tacl-1.95
Volume:
Transactions of the Association for Computational Linguistics, Volume 14
Month:
Year:
2026
Address:
Cambridge, MA
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
2103–2119
Language:
URL:
https://aclanthology.org/2026.tacl-1.95/
DOI:
10.1162/tacl.a.793
Bibkey:
Cite (ACL):
Minggui He, Yilun Liu, Shimin Tao, Hongyong Zeng, Jian Zhang, Yuanchang Luo, Li Zhang, Daimeng Wei, Weibin Meng, and Osamu Yoshie. 2026. R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning. Transactions of the Association for Computational Linguistics, 14:2103–2119.
Cite (Informal):
R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning (He et al., TACL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.tacl-1.95.pdf