arXiv Machine Learning September 24, 2026 By Niklas Scholz, David Thulke, Abdallah Nasir, Will Allred, Evgeny Matusov, Hermann Ney

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

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

arXiv Computation and Language

Oct 15

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

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.

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

llms nlp fine-tuning efficiency

arXiv Computation and Language

Sep 7

EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages

EuroAlpaca presents a task‑preserving localisation pipeline that translates English instruction‑tuning data into 50 European languages while maintaining task‑critical constraints. The method uses field‑wise machine translation or reconstructs task‑equivalent target‑language instances, followed by validation of coherence and consistency. Experiments show that EuroAlpaca improves instruction‑following accuracy by 12.9% over a baseline and outperforms direct translation on ROUGE‑L and F‑BERT metrics.

By Aleix Sant, Jordi Luque, Carlos Escolano

llms nlp fine-tuning benchmarks

arXiv AI

Oct 9

Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora

The study investigates how exposing large language models to Arabic translations of English benchmark tasks can hide data contamination from standard English-only detection methods. By testing four instruction-tuned models with increasing Arabic exposure, the authors find that traditional probes like TS-Guessing and Min-K%++ fail to detect contamination, yet English performance still improves. They propose a new Translation-Aware Contamination Detection (TACD) method that uses cross-lingual consistency and choice reordering to reveal contamination effects that are otherwise invisible to English-only diagnostics.

By Chaymaa Abbas, Nour Shammaa, Mariette Awad

llms benchmarks

arXiv AI

Oct 15

Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs

arXiv:2610.18818v2 Announce Type: cross Abstract: Pre-trained Large Language Model (LLMs) are effective on many tasks in zero-shot and few-shot settings. For machine translation of low-resource langu...

By Divyanshu Bathla, Parag Singla, Jitin Singla

llms nlp fine-tuning

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 Machine Learning

Jul 28

No Optimal Language Set Exists for Multilingual Instruction Tuning: Insights from a Linguistically-Informed Study

arXiv:2410. 07809v2 Announce Type: replace-cross Abstract: Multilingual instruction tuning (MIT) is challenged by the curse of multilinguality, data scarcity, and high computational cost.

By G\"urkan Soykan, G\"ozde G\"ul \c{S}ahin

fine-tuning benchmarks