Low-Resource MT

MT: Machine Translation

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 41

All topics

Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective
May 15, 2026Ernesto Garcia-Estrada, Carlos Escolano, José A. R. FonallosaGroup Relative Policy Optimization Low-Resource MT
Universitat Politècnica de Catalunya Barcelona, Spain
Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax
May 14, 2026Zeli Su, Ziyin Zhang, Zhou Liu +7Reinforcement Learning Low-Resource MT
Minzu University of China · Ant Group · Shanghai Jiao Tong University +4
WARDEN: Endangered Indigenous Language Transcription and Translation with 6 Hours of Training Data
May 13, 2026Ziheng Zhang, Yunzhong Hou, Naijing Liu +1Low-Resource MT Low-Resource Language Processing
Australian National University · University of Oxford
Towards Visually-Guided Movie Subtitle Translation for Indic Languages
May 12, 2026Tarun Chintada, Kshetrimayum Boynao Singh, Asif EkbalLow-Resource MT Low-Resource Language Processing
Department of Computer Science and Engineering Indian Institute of Technology Patna, India
Why do Large Language Models Fail in Low-resource Translation? Unraveling the Token Dynamics of Large Language Models for Machine Translation
May 8, 2026Shenbin Qian, Yves ScherrerMultilingual Language Model Evaluation Low-Resource MT
Language Technology Group, Department of Informatics University of Oslo, Norway
Data Contamination in Neural Hieroglyphic Translation: A Reproducibility Study
May 8, 2026Ammar Toutou, Abdelrahman Harb, Christine BastaBenchmark Contamination Low-Resource MT
Computer Science and Engineering, Alamein International University (AIU), Egypt · HiTZ Center, University of the Basque Country, Spain · Faculty of Computers and Data Science, Alexandria University, Egypt
Nsanku: Evaluating Zero-Shot Translation Performance of LLMs for Ghanaian Languages
May 5, 2026Stephen E. Moore, Mich-Seth Owusu, Akwasi Asare +13Multilingual Language Model Evaluation Open-Weight Language Models
Department of Mathematics, University of Cape Coast, Cape Coast, Ghana · Ghana Natural Language Processing, Cape Coast, Cape Coast, Ghana · Khaya AI LTD Ghana
Translating Under Pressure: Domain-Aware LLMs for Crisis Communication
Apr 29, 2026Antonio Castaldo, Maria Carmen Staiano, Johanna Monti +2Domain Adaptation Disaster Response
University of Pisa · University of Naples “L’Orientale” · University of Macerata +1
Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation
Apr 20, 2026Abhishek Purushothama, Emma Thronson, Alexia Guo +1In-Context Learning Low-Resource MT
Corpling Lab Georgetown University
An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages
Apr 3, 2026Yinhan Lu, Gaganpreet Jhajj, Chen Zhang +2In-Context Learning Low-Resource MT
Mila – Quebec AI Institute · McGill University · Athabasca University +2
A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books
Date pendingVarun Ghat Ravikumar, Sina Ahmadi, Lena Jäger +1LLM Fine-Tuning Synthetic Data Generation
Department of Informatics, University of Zurich · Department of Computational Linguistics, University of Zurich

May 15, 2026, cs.CLJ/K move · Enter open · S save

Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective

Ernesto Garcia-Estrada, Carlos Escolano, José A. R. Fonallosa

Universitat Politècnica de Catalunya Barcelona, Spain

Group Relative Policy Optimization Low-Resource MT RL Fine-Tuning Machine Translation

Open paper AskPDF arXiv

Production machine translation relies overwhelmingly on encoder-decoder Seq2Seq models, yet reinforcement learning approaches to MT fine-tuning have largely targeted decoder-only LLMs at

\geq

7B parameters, with limited systematic study of encoder-decoder architectures. We apply Group Relative Policy Optimization to NLLB-200 (600M and 1.3B) using a hybrid reference-free reward (LaBSE and COMET-Kiwi) that requires no parallel data at fine-tuning time, evaluating across 13 typologically diverse languages. GRPO yields consistent improvements on all 13 languages, up to

+

5.03 chrF++ for Traditional Chinese, and, without any target-language data, competes with 3-epoch supervised fine-tuning on morphologically complex languages . We identify a consistent empirical pattern in which gains are largest where baseline performance is weakest and reward discriminability is highest, making this approach most effective precisely where parallel data is scarcest, and replicate this pattern across English and Spanish source languages.

Momentum

Related topics

Latest papers 41