arXiv Computation and Language October 15, 2026 By Hao Wang, Yangyang Liu, Xiaohu Zhao, Heng Liu, Zifu Shang, Tianhao Li, Ruize Gao, Jialong Tang, Liangying Shao, Haoran Wei, Baosong Yang, Linlong Xu, Longyue Wang, Weihua Luo

Qwen-MT-Lumen at WMT2026: Instruction-Specialized Translation via Quality-Aware Training and On-Policy Distillation

Read the original on arXiv Computation and Language →

Qwen-MT-Lumen is an open‑source translation model submitted to the WMT 2026 General Machine Translation Shared Task. It employs a four‑stage pipeline that combines continued pre‑training, supervised fine‑tuning, online preference‑optimization with an LLM judge, and on‑policy distillation from a larger teacher to a Qwen3‑14B student. The system also uses structure‑aware inference and selective repair to preserve formatting and correct decoding errors, achieving an overall mean score of 4.60 on a 1–5 rubric and matching leading proprietary systems in both translation quality and instruction adherence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI

Aug 12

Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation

arXiv:2608. 10812v1 Announce Type: cross Abstract: We study reference-free post-training for multilingual machine translation with open large language models.

By Chris Han, Pengzhi Gao, Pei Fu, Jian Luan

llms nlp reinforcement-learning fine-tuning efficiency

arXiv Machine Learning

Sep 24

Fine-Tuning LLMs for Translation: General Forgetting Mitigation Does Not Preserve MT-Specific Instruction Following

Fine‑tuning large language models on parallel data can improve translation quality but also causes catastrophic forgetting of general capabilities. The study evaluates several forgetting‑mitigation methods—anchored to auxiliary data, model outputs, and base model parameters—using Llama 3.2 1B Instruct and Llama 3.1 8B Instruct on Arabic‑English and Spanish‑English translation tasks. Elastic Weight Consolidation best preserves general benchmark performance, yet only data mixing with control‑task examples maintains instruction‑following abilities such as formality and grammatical gender control, though these gains do not generalize to unseen prompts.

By Niklas Scholz, David Thulke, Abdallah Nasir, Will Allred, Evgeny Matusov, Hermann Ney

llms nlp fine-tuning benchmarks

arXiv Computation and Language

Sep 15

North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)

arXiv:2609.13916v1 Announce Type: new Abstract: We present North Small Translate, an open-weight, LLM-based machine translation (MT) model with instruction-following capabilities built on the same fo...

By Tom Kocmi, Alexandre B\'erard, Phil Blunsom, Samuel Cahyawijaya, Shaun Cassini, Nicholas Frosst, Ona de Gibert, Aidan Gomez, Nithya Govindarajan, Shun Kiyono, Olivia Lasche, Lawrence Rogers, Kelly Marchisio, Nikita Moghe, Yash More, Camila Moran-Hidalgo, Yiyang Nan, Michael Sachs, Trisha Starostina, Daan van Stigt, Spencer Rarrick, Sebastian Vincent, Ivan Zhang

llms agents nlp reinforcement-learning fine-tuning efficiency

arXiv Machine Learning

Aug 5

M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models

arXiv:2608. 03803v1 Announce Type: cross Abstract: Multilingual language models are deployed across a hundred or more languages, yet most benchmarks test whether a model can perform a task _in_ a language rather than whether it commands the language itself, conflating fluency with proficiency.

By Tom\'a\v{s} Burkert, Angelika Peljak-{\L}api\'nska, David Zelen\'y

llms nlp benchmarks safety

arXiv AI

Oct 16

Multi-SFT: Permissively-Licensed Multilingual Instruction-Following

Multi‑SFT is a new, commercially permissive dataset comprising 502,818 instruction‑response pairs in five European languages, created through translation and regeneration pipelines to address gaps where simple translation is insufficient. Human evaluation shows strong inter‑annotator agreement (≥0.87) across all languages. Fine‑tuning nine models from three families on Multi‑SFT yields performance competitive with larger, proprietary mixes and official instruction‑tuned releases, especially on safety‑related benchmarks.

By Daniela Baiamonte, Kamyar Zeinalipour, Elena Fano, Stefano Simonazzi, Andrea Zugarini

fine-tuning benchmarks safety

arXiv Computation and Language

Sep 10

MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages

arXiv:2607.00890v2 Announce Type: replace Abstract: Open web-scale pre-training corpora remain concentrated in English, limiting multilingual LLM development. We introduce MultiSynt/MT, an open synth...

By Maximilian Idahl, J\"org Tiedemann, Sampo Pyysalo, David Salinas, Tomasz Galica, Shenbin Qian, Tudor Nicolae Mateiu, Zihao Li, Anna Lokrantz, Fedor Vitiugin, Andr\'e F. T. Martins, Jenna Kanerva, Filip Ginter, Matthias Lindemann, Tim Isbister, Birger Moell, Jonas Lindh, Jan Haji\v{c}, Jenia Jitsev, Andrey Kutuzov, Stephan Oepen, Gema Ram\'irez-S\'anchez

llms benchmarks