Latest Machine Translation Research Papers

The newest Machine Translation papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Machine Translation so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Human-Based Machine Translation Evaluation: A Multi-Dimensional Approach to Sentiment, Emotion, and Argumentation Preservation in Chinese-English Translation
  Jingshi Zhou · University of Liverpool · Jan 1, 2028

  The research landscape of Machine Translation Evaluation (MTE) has traditionally been dominated by automated metrics that, while computationally efficient, often fail to capture the nuanced aspects of translation quality paramount to human …

• Nuha-Speech: Building General-Purpose Arabic Speech-LLMs
  Yingzhi Wang, Reem Alhazzani, Muhammad Alqurishi · arXiv · Sep 10, 2026

  As Speech Large Language Models (speech-LLMs) become increasingly multilingual, Arabic remains significantly underrepresented, highlighting the need for dedicated infrastructure to train and evaluate Arabic speech-LLMs. To address this gap,…

• Component-Aware Differential Privacy for Federated Multilingual Speech-LLMs
  Jordi Luque, Fernando López, Aleix Sant · arXiv · Sep 10, 2026

  Per-layer differential privacy (DP) clipping improves gradient fidelity in federated learning by allocating per-matrix clipping budgets proportional to parameter count. We show that this recipe breaks for speech large language models (speec…

• The Eloquence submission for Task 2 of the Interspeech 2026 MLC-SLM challenge
  Jordi Luque, Lorenzo Concina, Marco Matassoni, Alessio Brutti et al. · arXiv · Sep 10, 2026

  This paper details the Eloquence team's approach to Task 2 of the 2nd MLC-SLM challenge at Interspeech 2026, which involves multilingual Multiple-Choice Question Answering (MCQA) across 21 languages. Three approaches are explored. First, we…

• Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speech
  Tianlun Zuo, Ziyu Zhang, Tingzhi Mao, Zhonghua Fu et al. · arXiv · Sep 10, 2026

  Low-resource multilingual text-to-speech (TTS) systems have expanded language coverage, but their robustness under complex text inputs remains insufficiently diagnosed. Existing evaluations mainly focus on naturalness, speaker similarity, a…

• Structural priors for data-efficient language learning
  Yana Veitsman, Jonas Mayer Martins, Jonathan Lautenschlager, Lisa Beinborn · arXiv · Sep 10, 2026

  Efficient language learning requires methods to reduce the reliance on large data and computational resources. We investigate structural transfer: First training models on non-language data to induce useful priors for natural language. This…

• Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study
  Álvaro Rey-Blanes, Francisco J. Moreno-Barea, Francisco J. Veredas · arXiv · Sep 10, 2026

  Background: To determine whether cross-lingual clinical annotation projection can be formulated as a text-preserving, document-level generative task that produces verifiable character-level annotations for multilingual clinical corpus const…

• TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs
  Shenbin Qian, Yves Scherrer · arXiv · Sep 10, 2026

  Large language models (LLMs) are increasingly used for machine translation, yet their outputs often contain additional text beyond the translation itself, such as language labels, explanations or bilingual repetitions, which we term transla…

• SEAR: Segment-Evidence-Aware Routing for Weak-to-Strong Multilingual Speech MCQ
  Huy Hoang Le, Long-Bao Nguyen, Minh Tri Dao · arXiv · Sep 10, 2026

  This paper describes our system for Task~2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge. We adapt Qwen3-Omni-30B-A3B-Instruct with a segment-evidence-aware data and post-training pipeline. A language m…

• Beyond Solver Verdicts: Generative Reward Models for Autoformalization
  Vikash Singh, Debargha Ganguly, Aman Goel, Ali Torkamani et al. · arXiv · Sep 10, 2026

  Neurosymbolic systems rely on mathematical solvers to guarantee reasoning correctness, yet solvers are fundamentally blind to whether a formal translation maintains strict reference-equivalence to a designated formalization. We formalize th…

• Rosetta at AlexandriaX-2026: LoRA-Adapted NileChat for Context-Aware Dialectal Arabic Dialogue Translation
  Nada Esmaeil, Fathima Rena, Sibi Subhash, Osama Elgendy et al. · arXiv · Sep 9, 2026

  This paper describes the Rosetta system for Subtask 1 (Context-Aware English-to-Dialectal Arabic Dialogue Translation) of the AlexandriaX shared task, participating in both constrained and unconstrained tracks. The approach fine-tunes a LoR…

• NOPE-HYPE: A Structured Simulation Workflow for Robust Speech-to-Text Across Diverse Acoustic Environments
  Niramay M. Patel, Bibek Behera, Raksha Sharma · arXiv · Sep 9, 2026

  Robust speech-to-text translation systems should perform reliably across diverse acoustic conditions, yet practical pipelines lack controllable tools for systematic environment exploration. Large speech models remain sensitive to unseen aco…

• SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better Teachers
  Xixian Liao, Maite Melero · arXiv · Sep 9, 2026

  Terminology-aware translation asks for more than a correct translation: the output must use the exact terms a glossary prescribes. The standard recipe, fine-tuning on glossary-annotated translation pairs, hides an inefficiency: for most exa…

• Multi-Functional Embedding Models for Funder Name Disambiguation in Scientific Publication Records
  Kanyao Han, Zhiwen You, Jinseok Kim, Jana Diesner · arXiv · Sep 9, 2026

  Understanding the historical allocation and distribution of research funding advances our knowledge of how scientific research is supported across fields, institutions, and regions. However, large-scale analyses are hindered by the lack of …

• Improving Cross-Lingual Token Representations by Adding a Pinch of SALT
  Guillem Ramírez · arXiv · Sep 9, 2026

  Cross-lingual sentence encoders enable scalable transfer across hundreds of languages, powering applications such as translation mining and zero-shot learning in low-resource settings. Although trained for sentence-level alignment, they are…

• BuzzASR: A Swarm of 100+ Monolingual Speech Recognition Models
  Shivam Singh, Aditya Yadavalli, Catherine Arnett, Alex Warstadt · arXiv · Sep 9, 2026

  We introduce BuzzASR, a collection of language-specialized fine-tuned Whisper models adapted for automatic speech recognition (ASR) in 102 languages. Large end-to-end Transformer-based ASR models such as Whisper have revolutionized ASR, but…

• From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function Calls
  Hamed Jafarzadeh Asl, Yuanhao Yu, Vahid Partovi Nia · arXiv · Sep 8, 2026

  In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, making small language models (SLMs) attractive for on-device deployment. For such models, a key…

• SWORD: Wikidata-based Distortions Reveal Hidden Cross-Lingual Inconsistencies in LLM Factual Error Rejection
  Sanghyeok Park, Minji Kang, Hosung Kwak, Jinhyuk Yun · arXiv · Sep 8, 2026

  Modern LLMs demonstrate impressive multilingual performance, yet standard benchmarks primarily reward selecting correct answers rather than evaluating genuine factual understanding. We introduce Systematic Wikidata-based Object-Relation Dis…

• Improving Term Evaluation in Machine Translation: Variation Matters
  Nicolas Dahan, Ziqian Peng, François Yvon, Rachel Bawden · arXiv · Sep 8, 2026

  Terminology evaluation in machine translation (MT) usually assumes a single correct target form per source term. However, human translators routinely introduce variation that current metrics penalize as inconsistency. We examine how to acco…

• Same Values, Different Languages? From Multilingual Probing to Steering LLMs Toward Chinese Social Values
  Yuemei Xu, Kexin Xu, Jian Zhou, Haoyu Lu et al. · arXiv · Sep 8, 2026

  As Large Language Models (LLMs) are increasingly integrated into human society, aligning them with pluralistic social values has become a critical priority. However, whether LLMs exhibit consistent value preferences across languages remains…

• Compositional Multilingual and Behavioral Attribute Steering
  Hyun Gu Kang, Daniil Gurgurov, Tanja Baeumel, Josef van Genabith et al. · arXiv · Sep 8, 2026

  This study examines the compositionality of steering vectors for language and behavioral control in large language models. Focusing on language, jailbreak, and conciseness, we investigate whether additive, training-free composition of attri…

• Structural Jailbreaks Generalize but Do Not Compound: A cross-provider and multilingual study of Involuntary In-Context Learning
  Tejasvi C. Addagada · arXiv · Sep 8, 2026

  Aligned language models fail under two independent pressures: the structural jailbreak class recently formalized as Involuntary In-Context Learning (IICL), which reframes a harmful request as the final missing cell of a data-labeling task c…

• Tracing Stereotypes from Representation to Output in Multilingual LLMs
  Ariun-Erdene Tumurchuluun, Yusser Al Ghussin, Pinzhen Chen, Josef van Genabith et al. · arXiv · Sep 8, 2026

  Multilingual LLMs show stereotype-related behavior that varies across languages, but behavioral scores do not show where the relevant information is represented or how it affects the output. To investigate these internal mechanisms, we comp…

• EviSI: An Evaluation Agent for Simultaneous Interpreting
  Ben Yan, Zongyao Li, Daimeng Wei, Weidong Liu et al. · arXiv · Sep 8, 2026

  Simultaneous speech-to-speech translation requires understanding, translation and spoken delivery while the source stream continues. To support timely delivery and limit accumulated delay, systems adopt reformulation and summarization, whic…

• When Metrics Reward the Worst Translations: Internalizing Cultural Reasoning for Social Media Translation Evaluation
  Yiwen Qiu, Linjuan Wu, Dingming Li, Yizhou Liu et al. · arXiv · Sep 8, 2026

  Automatic translation quality metrics trained on general-domain corpora systematically fail on social media content, where communicative intent is encoded in culturally loaded expressions (internet slang, homophonic ciphers, and platform-sp…

• IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA
  Yuwen Chiu · arXiv · Sep 8, 2026

  We present the IGT system for PolyFiQA Task 2 of the FinMMEval Lab at CLEF 2026, a multilingual financial question answering task over English SEC filings and multilingual news articles (English, Chinese, Japanese, Spanish, Greek) for four …

• Rethinking Sign Language Translation: The Impact of Signer Dependence on Model Evaluation
  Keren Artiaga, Sabyasachi Kamila, Haithem Afli, Conor Lynch et al. · EMNLP 2025 · Sep 7, 2026

  Sign Language Translation has advanced with deep learning, yet evaluations remain largely signer-dependent, with overlapping signers across train/dev/test. This raises concerns about whether models truly generalise or instead rely on signer…

• EuroAlpaca: Task-Preserving Localisation of Instruction Data for European Languages
  Aleix Sant, Jordi Luque, Carlos Escolano · arXiv · Sep 4, 2026

  Machine translation (MT) offers a scalable way to extend English instruction-tuning data to multiple languages, but it can distort task-critical constraints and required outputs, creating corrupted training examples and degrading models tra…

• Discourse Dependency: A Continuous Criterion for Translation Difficulty
  Ahrii Kim, Chanjun Park, Seong-heum Kim · arXiv · Sep 4, 2026

  Recent calls for harder machine translation benchmarks have not clarified what difficulty should mean. We argue that one meaningful and currently unmeasured axis is referential reach, the distance a segment must look back into its document …

• MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain
  Sourav Malakar, Harshit Nigam, Akash Ghosh, Sriparna Saha et al. · arXiv · Sep 4, 2026

  Time-series data in clinical settings is crucial for capturing dynamic changes in a patient's health over time, enabling timely diagnosis, personalized treatment, and early detection of critical events. However, the development of clinicall…