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

Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions
May 22, 2026Anastasiia Sedova, Natalie Schluter, Skyler Seto +1Language Model Pretraining Multilingual Language Models
1Apple
Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
May 21, 2026Yusser Al Ghussin, Daniil Gurgurov, Tanja Baeumel +3Multilingual Language Models Language Model Steering
Saarland University · German Research Center for Artificial Intelligence (DFKI) · Centre for European Research in Trusted AI (CERTAIN) +1
Brain-LLM Alignment Tracks Training Data, Not Typology
May 21, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuMultilingual Language Models Cross-Lingual Representation Alignment
The University of Hong Kong Hong Kong, China · Stellaris AI Limited Hong Kong, China
Moral Semantics Survive Machine Translation: Cross-Lingual Evidence from Moral Foundations Corpora
May 21, 2026Maciej SkorskiLow-Resource Language Processing Cross-Lingual Transfer
University of Luxembourg Faculty of Science, Technology and Medicine Luxembourg, Luxembourg · University of Warsaw Institute of Informatics Warsaw, Poland
Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
May 21, 2026Andrew Ivan Soegeng, Patrick Sutanto, Tan Sang NguyenCultural Bias in Language Models Cultural Knowledge in Language Models
SAP · School of Computing, National University of Singapore
StyleTextGen: Style-Conditioned Multilingual Scene Text Generation
May 14, 2026Zeyu Chen, Fangmin Zhao, Yan Shu +3Text Generation Cross-Lingual Transfer
1Nankai University · Institute of Information Engineering, Chinese Academy of Sciences · University of Trento
DiM\textsuperscript{3}: Bridging Multilingual and Multimodal Models via Direction- and Magnitude-Aware Merging
May 13, 2026Zijing Wang, Mingyang Wang, Ercong Nie +6Multilingual Language Models Multimodal Large Language Models
Northeastern University, China · CIS, LMU Munich, Germany · Munich Center for Machine Learning (MCML), Germany +1
What makes a word hard to learn? Modeling L1 influence on English vocabulary difficulty
May 12, 2026Jonas Mayer Martins, Zhuojing Huang, Aaricia Herygers +1Cross-Lingual Transfer
University of Göttingen, Germany
Why Low-Resource NLP Needs More Than Cross-Lingual Transfer: Lessons Learned from Luxembourgish
May 11, 2026Fred Philippy, Siwen Guo, Jacques Klein +1Low-Resource Language Processing Cross-Lingual Transfer
1SnT, University of Luxembourg, Luxembourg · 2Luxembourg Institute of Science and Technology, Luxembourg
Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
May 10, 2026Yihong Liu, Raoyuan Zhao, Michael A. Hedderich +1On-Policy Self-Distillation Cross-Lingual Reasoning in Language Models
Center for Information and Language Processing, LMU Munich · Munich Center for Machine Learning (MCML)
Cross-Cultural Transfer of Emoji Semantics and Sentiment in Financial Social Media
May 10, 2026Ahmed Mahrous, Roberto Di PietroSocial Media Analysis Sentiment Analysis
King Abdullah University of Science and Technology (KAUST)
From Traditional Taggers to LLMs: A Comparative Study of POS Tagging for Medieval Romance Languages
May 9, 2026Matthias Schöffel, Esteban Garces AriasMultilingual Language Model Evaluation Morphosyntactic Tagging
Bavarian Academy of Sciences (BAdW), Munich, Germany · Department of Statistics, LMU Munich, Germany · Munich Center for Machine Learning (MCML), LMU Munich, Germany
Language-Conditioned Visual Grounding with CLIP Multilingual
May 9, 2026J. de Curtò, Mauro Liz, I. de ZarzàVLM Evaluation Multilingual VLM Evaluation
Department of Computer Applications in Science & Engineering, BARCELONA Supercomputing Center, Barcelona, Spain · Estudis d’Informàtica, Multimèdia i Telecomunicació, Universitat Oberta de Catalunya, Barcelona, Spain · Escuela T´ecnica Superior de Ingenier´ıa (ICAI), Universidad Pontificia Comillas, Madrid, Spain +2
Improving Lexical Difficulty Prediction with Context-Aligned Contrastive Learning and Ridge Ensembling
May 9, 2026Wicaksono Leksono Muhamad, Joanito Agili Lopo, Tsamarah Rana Nugraha +2Contrastive Learning Cross-Lingual Transfer
Mantera Studio · The University of Manchester · Universitas Gadjah Mada
TajPersLexon: A Tajik-Persian Lexical Resource and Hybrid Model for Cross-Script Low-Resource NLP
May 7, 2026Mullosharaf K. ArabovLow-Resource Language Processing Cross-Lingual Transfer
Institute of Computational Mathematics and Information Technologies Kazan Federal University Kazan, Russia
In Data or Invisible: Toward a Better Digital Representation of Low-Resource Languages with Knowledge Graphs
May 7, 2026Ndeye-Emilie MbengueAnalogical Reasoning Low-Resource Language Processing
WIMMICS · Université Côte d’Azur, Inria, CNRS, I3S, Sophia-Antipolis, France
Understanding Cross-Language Transfer Improvements in Low-Resource HTR: The Role of Sequence Modeling
May 7, 2026Sana Al-azzawi, Chang Liu, Nudrat Habib +2Convolutional RNNs Recurrent Neural Networks
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering , Luleå, Sweden · Luleá University of Technology, Department of Computer Science, Electrical and Space Engineering , Luleå, Sweden
Harnessing Linguistic Dissimilarity for Language Generalization on Unseen Low-Resource Varieties
May 6, 2026Jinju Kim, Haeji Jung, Youjeong Roh +2Low-Resource Language Processing Dependency Parsing
Department of Electrical and Computer Engineering, Sungkyunkwan University · Language Technologies Institute, Carnegie Mellon University · Department of Computer Science, University of British Columbia +1
The Impact of Vocabulary Overlaps on Knowledge Transfer in Multilingual Machine Translation
May 5, 2026Oona Itkonen, Jörg TiedemannMachine Translation Cross-Lingual Transfer
University of Helsinki
MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing
May 4, 2026Liwei Cheng, Shibo Feng, Lunjie Zhou +2Image Editing Evaluation Text-Guided Image Editing
1Harbin Institute of Technology
Cross-Lingual Learning within Arabic Script for Low-Resource HTR
May 3, 2026Sana Al-azzawi, Elisa Barney, Marcus LiwickiOnline Handwriting Recognition Low-Resource Language Processing
Luleå University of Technology Department of Computer Science, Electrical and Space Engineering Luleå, 97187, Sweden
Multilingual Safety Alignment via Self-Distillation
May 3, 2026Ruiyang Qin, Qingzhuo Wang, Dongrui Liu +3Multilingual Language Models LLM Safety Alignment
Tongji University · Shanghai AI Laboratory
Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations
May 2, 2026Pratyush Acharya, Nuraj Rimal, Habish DhakalTransformer Interpretability Representation Learning
Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus
May 1, 2026Daria Boratyn, Damian Brzyski, Albert Leśniak +5Semantic Textual Similarity Text Embedding Evaluation
aJagiellonian Center for Quantitative Political Science, Jagiellonian University, Kraków, Poland · bAGH University, Kraków, Poland · cJagiellonian Center for Digital Humanities, Jagiellonian University, Kraków, Poland
Selective Augmentation: Improving Universal Automatic Phonetic Transcription via G2P Bootstrapping
Apr 29, 2026Tobias Bystrich, Julia M. Pritzen, Christoph A. Schmidt +1Data Augmentation G2P Conversion
Fraunhofer Institute IAIS, Sankt Augustin, Germany · University of Bonn, Bonn, Germany
Zero-Shot to Full-Resource: Cross-lingual Transfer Strategies for Aspect-Based Sentiment Analysis
Apr 29, 2026Jakob Fehle, Nils Constantin Hellwig, Udo Kruschwitz +1Multilingual Language Model Evaluation Aspect-Based Sentiment Analysis
Media Informatics Group, University of Regensburg, Regensburg, Germany · Information Science Group, University of Regensburg, Regensburg, Germany
CroSearch-R1: Better Leveraging Cross-lingual Knowledge for Retrieval-Augmented Generation
Apr 28, 2026Rui Qi, Fengran Mo, Sijin Lu +3Retrieval-Augmented Generation Multilingual IR
School of Computer Science and Technology, Beijing Jiaotong University Beijing, China · RALI, Université de Montréal Montréal, Québec, Canada
Large Language Models for Multilingual Code Intelligence: A Survey
Apr 27, 2026Chao Jiang, Dugang Liu, Cheng Wen +6Code Translation Code Generation
College of Computer Science and Software Engineering, Shenzhen University, China · Guangzhou Institute of Technology, Xidian University, China · Guangzhou University of Software, China +2
IRIS: Interleaved Reinforcement with Incremental Staged Curriculum for Cross-Lingual Mathematical Reasoning
Apr 27, 2026Navya Gupta, Rishitej Reddy Vyalla, Avinash Anand +8Cross-Lingual Reasoning in Language Models RL for Language Model Reasoning
1Singapore Institute of Technology, Singapore · 2IIIT Delhi, New Delhi, India · University of California, San Diego, USA +2
XITE: Cross-lingual Interpolation for Transfer using Embeddings
Apr 26, 2026Barah Fazili, Preethi JyothiMultilingual Language Models Data Augmentation
Indian Institute of Technology Bombay, India

May 22, 2026J/K move · Enter open · S save

Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions

Anastasiia Sedova, Natalie Schluter, Skyler Seto, Maartje ter Hoeve

1Apple

Language Model Pretraining Multilingual Language Models Low-Resource Language Processing Cross-Lingual Transfer

Open paper AskPDF arXiv

Cross-lingual knowledge transfer is critical for building high-performing multilingual language models for languages with insufficient training data. When target language data is scarce, the knowledge required for many downstream tasks involving scientific reasoning, commonsense inference, and world knowledge must be acquired primarily from the high-resource language, making effective knowledge transfer essential. Existing methods for improving such cross-lingual knowledge transfer require large amounts of parallel data, translation systems, auxiliary models, or additional training stages that are largely unavailable for many languages. We propose LINK - a data-level intervention method that improves knowledge transfer during model pretraining through lexical substitutions in high-resource part of pretraining data using bilingual vocabularies. For a given replacement ratio, randomly selected words in a portion of the high-resource (English) training corpus are swapped with their word-level translations, requiring no additional model training and only a bilingual vocabulary, which can be obtained at near-zero cost for virtually any language. Evaluation on eight languages across five model sizes shows notable improvements on downstream tasks in the target language, with up to a 2x speedup in training to reach equivalent performance.