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 …

• Video Game Localisation and Culturalisation- From Traditional Translation Theory to AI-assisted Applications
  Peishu Wang · University of Liverpool · Jan 1, 2027
• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
  Max Neuwinger, Hanna Yukhymenko, Imanol Schlag · arXiv · Oct 29, 2026

  Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance. Related open training datasets are often limited in size or do not f…

• Mobilizing the Archive: Bitext Extraction at Scale from Archival Documents for Extremely Low-resource Languages
  Chutong Meng, Alec J. Bateman, Antonios Anastasopoulos · arXiv · Oct 29, 2026

  While mining parallel sentences from web pages has proven effective for low-resource machine translation, the majority of the world's languages have little to no web presence. What they do have, though, are resources that are the result of …

• A Novel Approach to Evaluating Evaluation Metrics for Multi-Output Structured Prediction
  Akshay Vyas, Angelo Pimienta, Nicholas Ruozzi · AAAI · Oct 29, 2026

  In multi-output structured prediction tasks, while only one ground truth label may be provided in the training data, multiple equally valid outputs may be possible, making reliable evaluation a persistent challenge. We postulate that human …

• Gold vs.~Translation: Are We Measuring Language, Knowledge, or Locality in Translated Benchmarks?
  Klaudia-Doris Thellmann, Bernhard Stadler, Dan Saattrup Nielsen, Michael Färber et al. · EMNLP 2026 · Oct 28, 2026

  Translated versions of English-origin benchmarks such as MMLU are widely used to evaluate large language models in non-English languages, yet it remains unclear whether they measure the same constructs as natively created benchmarks. We fra…

• Leaving the Cave by Breaking the Symmetry: Identifiable Structure Can Enable Cross-Lingual Generalization
  Frederick Riemenschneider, Anette Frank · arXiv · Oct 28, 2026

  Why do multilingual language models generalize across languages even without shared vocabulary? The Platonic Representation Hypothesis posits that models trained on different data, objectives, and modalities converge toward a shared statist…

• The State and Fate of Multilingual, Contextual Evaluation in the NLP World
  Manan Uppadhyay, Himanshu Beniwal, Prashant Kodali, Sunayana Sitaram · COLM · Oct 27, 2026

  Multilingual evaluation benchmarks are the primary instrument for assessing whether large language models generalize beyond English, yet the adequacy of these benchmarks has received little systematic scrutiny. We present a data-driven audi…

• DocSkill: Skill-Integrated Agentic Reasoning for Multilingual Multi-Hop Document Question Answering
  Jing Huang, Zhiya Tan, Changtao Miao, Shutao Gong et al. · arXiv · Oct 27, 2026

  Multilingual multi-hop document question answering (MMHop-DocQA) requires locating and integrating evidence across complex layouts, document pages, and diverse languages. Existing approaches include single-pass processing and adaptive tool …

• Japanese Discourse Structure Analysis Based on Segmented Discourse Representation Theory Using LLMs
  Satomu Tomisaki, Yosuke Mikami, Amane Watahiki, Hitomi Yanaka · arXiv · Oct 27, 2026

  Discourse parsing based on Segmented Discourse Representation Theory (SDRT) is crucial for capturing the structural dynamics of dialogues. However, most prior research focuses on English, and its effectiveness for Japanese remains unclear o…

• Agentic Data Sampling Framework for Multilingual ASR via Linguistic-Aware Error-Driven Optimization
  Zhiheng Qian, Junhao Du, Jing Peng, Hanqi Li et al. · arXiv · Oct 27, 2026

  Multilingual automatic speech recognition (ASR) has achieved rapid progress with large-scale pretrained models and multilingual speech corpora. Previous studies have proved the pivotal role of data sampling in multilingual ASR performance. …

• ETC-Bench: A Multilingual Benchmark for Evaluation-Side Transcript Canonicalization
  Zhiheng Qian, Junhao Du, Jing Peng, Hanqi Li et al. · arXiv · Oct 27, 2026

  Written transcripts of the same speech can differ in ways that are not uniquely determined by the speech signal. We formulate evaluation-side transcript canonicalization (ETC), which maps multiple surface forms to a single canonical form wh…

• Preserve to Expand: Source-Aware Adaptation and Model Merging for Multilingual LLM-Based ASR
  Yuchen Zhang, Haralambos Mouratidis, Ravi Shekhar · arXiv · Oct 26, 2026

  Expanding multilingual ASR systems to new languages is challenging when adaptation must preserve previously supported languages without replaying source-language training data. We study this problem in connector-based Speech LLMs, where a t…

• Beyond Words Alone: Disentangling Distributed Evidence for Visually Grounded Cultural Translation
  Dingming Li, Yiwen Qiu, Linjuan Wu, Hongxing Li et al. · arXiv · Oct 26, 2026

  Social media enables cross-lingual communication, yet the meaning of user-generated content (UGC) is often distributed across text, images, and cultural knowledge, making translation challenging. Existing evaluations typically treat images …

• INVAR-Agri: Detecting Discrepancies in Multilingual Operator Manuals of Agricultural Implements with a Fine-Tuned LLM
  Timo Oksanen · arXiv · Oct 26, 2026

  Operator manuals of agricultural implements are delivered in many languages, and the standards require that competent persons review every translation, which makes this review the bottleneck. This paper presents a proof of concept that comp…

• ImgMT: Wikipedia-based Dataset For Evaluating Text-in-Image Translation
  Šárka Uramová, Petar Kirilov Petrov, Josef Jon, Ondřej Bojar et al. · arXiv · Oct 26, 2026

  Text-in-image translation aims to translate all textual content embedded in an image. In Text Image Translation (TIT), the output is translated text; In-Image Machine Translation (IIMT) additionally renders the translation back into the ima…

• The Lay of the Land in Idiom-Translation Quality Estimation
  Malik Marmonier, Benoît Sagot, Rachel Bawden · arXiv · Oct 26, 2026

  Idioms have long been a challenge for machine translation, and while large language models (LLMs) have proven increasingly adept at handling them, whether quality estimation (QE) systems have kept pace and can reliably score idiomatic rende…

• Lost in Translation: Investigating Systematic Discrepancies between Parallel English and Chinese Names of American Chinese Restaurants
  Hang Jiang, Nanxi Liu, Tiantian Wang, Cassandra Overney et al. · arXiv · Oct 26, 2026

  Given that the Chinese are one of the oldest ethnic groups to immigrate to the US, their cuisine have become central to the US dining scene and an interesting avenue to study how Chinese immigrants have culturally adapted into American life…

• High Scores, Hidden Failures: Evaluating Codebook-Based LLM Content Analysis
  Elena Senger, Yuri Campbell, Rob van der Goot, Barbara Plank · arXiv · Oct 26, 2026

  Large language models (LLMs) are increasingly used for codebook-based content analysis in computational social science, where codebooks translate theoretical concepts into labeling schemes. While prior work reports strong predictive perform…

• Do Language Models Understand Igbo Culture? Beyond Multiple Choice
  Blessing Ngozi Uzor, Valdini Douglace Lemofouet, Paula Chikaodinaka Anyanwu, Tassallah Abdullahi et al. · arXiv · Oct 26, 2026

  The value of language models for any community depends on whether a model actually understands the culture of the people it intends to serve. We use the Igbo language as a case study. Existing benchmarks test translated Western ideas, lacki…

• Quality over Quantity: Rethinking Data and Model Assumptions for Bengali Coreference Resolution
  Zenith Biswas, Andrew Thomas Dyer · arXiv · Oct 26, 2026

  Multilingual transformer models are often assumed to generalise across languages, but their effectiveness for coreference resolution in low-resource settings remains unverified. We investigate this gap in Bengali, a language with over 250 m…

• From Questions to Queries to Insights: A Schema-Grounded Agentic Workflow for Natural-Language Crash Data Analysis
  Jingwen Zhu, Keshu Wu, Steven T. Parker, Bin Ran et al. · arXiv · Oct 26, 2026

  Transportation agencies maintain extensive crash databases to identify safety priorities, evaluate countermeasures, and guide resource allocation. Making these data accessible to practitioners requires flexible ways to translate analytical …

• SimPOTrans: Self-Adaptation for Offline-to-Simultaneous Speech Translation via Reinforcement Learning
  Haotian Tan, Hiroki Ouchi, Sakriani Sakti · arXiv · Oct 26, 2026

  Simultaneous speech translation (SimulST) aims to translate ongoing speech with low latency while preserving translation quality. Recent studies have adopted large language models (LLMs) for SimulST and formulated it as a multi-turn dialogu…

• Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox
  Federico Lucca · arXiv · Oct 23, 2026

  Personal email agents decide, for every message, what it is, whether it is urgent, whether to draft a reply, create a task, or ignore it. Their error rate is rarely measured: the stored labels were written by the system itself. We present F…

• Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model
  Yalda Taheri, Mohammad Hassan Heydari, Armon Rasooli · arXiv · Oct 23, 2026

  Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training resources and compact embedding models. We present Yalda Embedding, a…

• Communicating with the Entire Population: Machine Translation of Emergency Alerts and Warnings
  Jen Wilson, Vipasha Bansal, William D. Lewis · arXiv · Oct 23, 2026

  It is essential that we communicate with the entirety of an affected population during a crisis, including those who do not speak a region's dominant language(s). Commercial Translation tools offer a tempting solution to broaden access and …

• ParaTaxe: a Suite of Tools for Processing and Publishing Multi-parallel Corpora
  Olivier Kraif, Cyrille François, Elnaz Jalilian, Natacha Rimasson-Fertin et al. · arXiv · Oct 23, 2026

  Over the past fifteen years, digital tools for parallelizing and aligning textual corpora have developed significantly within the field of digital humanities. Several projects and software tools have been created to compare different transl…

• The Butterfly Defects: Tracing Cooperation in LLM Agent Networks
  Maria Sampani, Maria Lymperaiou, Angeliki Dimitriou, Giorgos Filandrianos et al. · arXiv · Oct 23, 2026

  As large language models (LLMs) increasingly operate as interconnected agents, a fundamental question emerges: does individual cooperation translate into collective cooperation? We investigate this question through the Iterated Prisoner's D…

• When is more search useful? An Empirical Study of Search Utility in Quality-Aware Decoding for Machine Translation
  Javier Garcia Gilabert, Rico Sennrich, André F. T. Martins · arXiv · Oct 23, 2026

  Quality-Aware Decoding (QAD) improves machine translation through test-time scaling, generating multiple candidate translations and selecting the final output with a quality-aware decoder. Usually the same candidate budget N is spent on eve…