Cross-Lingual Transfer

Follow this topic Ask about this topic

Latest papers 240

30 papers in the last four weeks, up 25% on the four weeks before. 0.2% of all new papers.

All topics

Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains
Sep 14, 2026Quang Phuoc Nguyen, Félix Gaschi, David Anugraha +2Multilingual Language Models Cross-Lingual Representation Alignment
1Ontario Tech University · 2Doctrine · 3Stanford University +2
Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study
Sep 10, 2026Álvaro Rey-Blanes, Francisco J. Moreno-Barea, Francisco J. VeredasLLM-Assisted Annotation Controllable Text Generation
Department of Programming Languages and Computer Sciences, Universidad de Málaga, Málaga, Spain · Research Institute of Multilingual Language Technologies, Universidad de Málaga, Málaga, Spain · IBIMA Plataforma BIONAND, Instituto de Investigación Biomédica de Málaga, Málaga, Spain
Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
Sep 9, 2026Mehrnaz Mofakhami, Ananya Sahu, Alejandro R. Salamanca +5Multilingual Language Models Cross-Lingual Reasoning in Language Models
Cohere Labs · Cohere
Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy
Sep 7, 2026Ayoub Kirouane, Georgios Giaples, Christos PetrocheilosVision-Language-Action Models Cross-Lingual Transfer
Sophea AI, KIEFER SA, Athens, Greece
Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3
Sep 4, 2026Giang Son Nguyen, Nhi Ngoc-Yen Nguyen, Wray Buntine +1Cross-Lingual Consistency in Language Models Cross-Lingual Transfer
VinUniversity · Nanyang Technological University · University of Science and Technology of China +1
PolERo: Studying Political Evasion in Romanian
Sep 2, 2026Gabriel Stefan, Sergiu NisioiPolitical Discourse Analysis Cross-Lingual Transfer
Laboratory for Cybernetic Research and Good Life Human Language Technologies Research Center Faculty of Mathematics and Computer Science University of Bucharest
MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution Shifts
Sep 2, 2026Matteo Greco, Anudeex Shetty, Andrea Tagarelli +1Authorship Attribution Cross-Lingual Transfer
School of Computing and Information Systems, The University of Melbourne, Australia · DIMES Dept., University of Calabria, Italy
Probing Factual Knowledge Transfer with Training Data Interventions
Sep 1, 2026Romina Oji, Marc Braun, Marcel Bollmann +2Language Model Pretraining Multilingual Language Model Evaluation
Department of Computer and Information Science Linköping University
The Interlingua Hypothesis: LLMs Translate via a Latent Task-agnostic Feature Space
Sep 1, 2026Jacob Brinton, Jannik Brinkmann, Mark Crovella +1Multilingual Language Models Machine Translation
Boston University · Technische Universität Clausthal
Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation
Aug 31, 2026Ran Zhang, Miryam de Lhoneux, Wessel PoelmanContinued Pretraining Low-Resource Language Processing
LAGOM·NLP, Department of Computer Science, KU Leuven
Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer
Aug 31, 2026Minju Song, Hyeon Hwang, Junhyun Lee +1Cross-Lingual Reasoning in Language Models Low-Resource Language Processing
Korea University · Hankuk University of Foreign Studies · Noah’s Farm +1
Generative Models Enhanced by Sequence Labelling and Aspect-Code Switching Improve Cross-lingual Aspect-Based Sentiment Analysis
Aug 31, 2026Jakub Šmíd, Pavel Přibáň, Pavel KrálAspect-Based Sentiment Analysis Cross-Lingual Transfer
Department of Computer Science and Engineering · NTIS – New Technologies for the Information Society · University of West Bohemia in Pilsen, Faculty of Applied Sciences +1
Cross-lingual Functional Vectors for Emotion Detection in Large Language Models
Aug 30, 2026Jieying Xue, Phuong Minh Nguyen, Minh Le Nguyen +1Cross-Lingual Transfer Multilingual Language Models
Japan Advanced Institute of Science and Technology
Toward a Cross-Lingual Romanization Ecosystem for Sinitic Languages: A Paired Mandarin-Cantonese Case Study
Aug 29, 2026Zijie Zhang, Tan Lee, Yong Cao +1Cross-Lingual Transfer
The Chinese University of Hong Kong, Shenzhen
Is Prosody Lost in Translation? Fine-Grained Cross-Lingual Prosody Similarity Across Languages
Aug 28, 2026Haopeng Xie, Ismail Rasim Ulgen, Sofia Son +2Speech Prosody Cross-Lingual Transfer
Center for Language and Speech Processing (CLSP), Johns Hopkins University Baltimore, MD, USA
The Curse of Multilinguality in Lexical Normalization
Aug 27, 2026Saman RahbarMultilingual Language Models Cross-Lingual Transfer
Independent Researcher
What Can Low Resource Languages Learn From Each Other?
Aug 27, 2026Achyuth P, Kahaan Shah, Chetan AroraOptical Character Recognition VLM Adaptation
IIT Delhi, New Delhi, India
TransMeme: A Multi-Agent Framework for Cross-Cultural Meme Transcreation
Aug 27, 2026Jingyi Zheng, Yule Liu, Zifan Peng +4Cross-Lingual Transfer Multi-Agent Systems
Hong Kong University of Science and Technology (Guangzhou) · Aarhus University · Wuhan University
Cross-lingual Representation Learning via Centroid Intervention Fusion
Aug 26, 2026Wei Sun, Marie-Francine MoensCross-Lingual Transfer Causal Interventions in Language Models
Department of Computer Science, KU Leuven Celestijnenlaan 200A 3001 Heverlee, Belgium
One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography
Aug 26, 2026Muge Zhang, Aaron Jencks, Krishna Badikela +2Language Model Pretraining Multilingual Language Models
Department of Computer Science and Engineering, Ohio State University · Paul G. Allen School of Computer Science & Engineering, University of Washington
Dataset Scarcity Limits Robust Evaluation of Multilingual Embedding Models: A Case Study of Slavic Languages
Aug 25, 2026Ana Gjorgjevikj, Barbara Koroušić Seljak, Tome EftimovMultilingual Language Model Evaluation Text Embedding Evaluation
Computer Systems Department Jožef Stefan Institute Ljubljana, Slovenia
The Multilingual FrameNet Corpus
Aug 24, 2026Beatrice Fiumanò, Nicolas Lazzari, Simone Paolo Ponzetto +1Semantic Parsing Cross-Lingual Transfer
University of Bologna, Italy · University of Pisa, Italy · University of Mannheim, Germany
ProBel: Propaganda Detection with Techniques, Spans, and Explanations
Aug 23, 2026Mohamed Bayan Kmainasi, Ali Ezzat Shahroor, Elisa Sartori +2Text Classification Cross-Lingual Transfer
Qatar Computing Research Institute, Qatar · University of Padova, Italy
LëtzCross: A Cross-Lingual Page-Level Benchmark for Multimodal Retrieval over Luxembourgish Documents
Aug 22, 2026Omar El Bachyr, Fred Philippy, Laura Maria Bernardy +3Multilingual IR Visual Document Retrieval
University of Luxembourg, Luxembourg · King Fahd University of Petroleum and Minerals, Saudi Arabia
Cross-Sign Language Transfer Learning Using Domain Adaptation with Multi-scale Temporal Alignment
Aug 17, 2026Keren Artiaga, Yang Li, Ercan Engin Kuruoglu +2Sign Language Recognition Cross-Lingual Transfer
Victor · Tsinghua-Berkeley Shenzhen Insitute, Tsinghua Shenzhen International Graduate School, The University Town, Nanshan District, Shenzhen, 518055, P.R.China.
Hard Negatives Reveal What Easy Negatives Hide: Cross-Lingual Harmfulness Representations Degrade with Resource Tier Under Hard Negatives
Aug 15, 2026Paras Balani, Subhrakanta PandaLanguage Model Safety Evaluation Cross-Lingual Transfer
Department of Mathematics and Department of Computer Science, Birla Institute of Technology and Science, Pilani, Hyderabad Campus, Jawahar Nagar, Kapra Mandal, Medchal District, Telangana 500078, India · Department of Computer Science, Birla Institute of Technology and Science, Pilani, Hyderabad Campus, Jawahar Nagar, Kapra Mandal, Medchal District, Telangana 500078, India
GRPO Beyond English: A Large-Scale Study of GRPO in Non-English and Multilingual Settings
Aug 13, 2026Konstantin Dobler, Federico Scozzafava, Jonathan Janke +2Cross-Lingual Reasoning in Language Models RL for Language Model Reasoning
Apple · 1Hasso Plattner Institute & ELLIS Unit Potsdam (work done during Apple internship)
Cross Lingual Transfer in Tulu Legal Comprehension: Script-Dependent Improvement and RAG-Induced Knowledge Conflict
Aug 13, 2026Sindhu Shetty, Spurthi Setty, Natan VidraLow-Resource Language Processing Cross-Lingual Transfer
Motor, Cognitive, or Corpus? What Survives Cross-Lingual Transfer in Speech-Based Parkinsons Disease Detection
Aug 13, 2026Serli Kopar, Sam Gijsen, Abner Hernandez +2Speech Processing Parkinson's Disease
Hertie Institute for AI in Brain Health, University of Tübingen, Tübingen, Germany · Tübingen AI Center, University of Tübingen, Tübingen, Germany · Charité–Universitätsmedizin, Department of Psychiatry and Psychotherapy, Berlin, Germany +1
Behavioral Reprogramming of Open-Weights Models: Cognitive Plasticity and Alignment Bounds
Aug 13, 2026Lucia MalíčkováLLM Alignment Language Model Steering
National Supercomputing Centre, Slovakia.

Sep 14, 2026J/K move · Enter open · S save

Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains

Quang Phuoc Nguyen, Félix Gaschi, David Anugraha, Santiago Martínez Novoa+1

1Ontario Tech University · 2Doctrine · 3Stanford University+2

Multilingual Language Models Cross-Lingual Representation Alignment Adaptive Sampling Low-Resource Language Processing Cross-Lingual Transfer

Open paper AskPDF arXiv

Realignment is a promising approach for improving the cross-lingual transfer ability of multilingual language models, particularly for extremely low-resource languages (LRLs). However, existing realignment methods rely on uniform and random sampling of parallel sentences across languages, which may be suboptimal under limited batch sizes. In practice, models may benefit from seeing certain languages more frequently, especially those that are poorly aligned, and the optimal distribution can evolve throughout training. In this work, we propose a simple yet effective adaptive sampling strategy that assigns trainable sampling probabilities to each language. Languages that contribute more to the realignment loss are sampled more frequently in subsequent batches, and the optimal distribution can evolve throughout training. Our method employs an inner-outer optimization loop with a small overhead, leading to consistent performance improvements and, more importantly, distributing the gains across languages. We observed a

+0.67

average performance increase on all tasks with XLM-R, and

+0.60

with Gemma 2 9B compared with uniform realignment. Furthermore, our method is robust across different models. Code available at https://github.com/felixgaschi/multilingual-alignment-and-transfer.