Cross-Lingual Transfer

Follow this topic Ask about this topic

Latest papers 239

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

All topics

Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders
Mar 19, 2026Yana Veitsman, Yihong Liu, Hinrich SchützeCross-Lingual Representation Alignment Cross-Lingual Transfer
University of Göttingen · LMU Munich · Munich Center for Machine Learning (MCML)
Cross-Lingual LLM-Judge Transfer via Evaluation Decomposition
Mar 19, 2026Ivaxi Sheth, Zeno Jonke, Amin Mantrach +1Cross-Lingual Transfer Cross-Cultural Language Model Evaluation
CISPA Helmholtz Center for Information Security · Amazon
ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws
Mar 18, 2026Xuyang Cao, Qianying Liu, Chuan Xiao +7Language Model Scaling Laws Multilingual Language Models
NII LLMC · The University of Osaka · Nara Institute of Science and Technology +2
Language on Demand, Knowledge at Core: Composing LLMs with Encoder-Decoder Translation Models for Extensible Multilinguality
Mar 18, 2026Mengyu Bu, Yang FengMultilingual Language Models Cross-Lingual Transfer
Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS) · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences, Beijing, China
Large Reasoning Models Struggle to Transfer Parametric Knowledge Across Scripts
Mar 17, 2026Lucas Bandarkar, Alan Ansell, Trevor CohnCross-Lingual Transfer Cross-Lingual Reasoning in Language Models
University of California, Los Angeles · Google Research · University of Melbourne
Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?
Mar 17, 2026Aishwarya Ramasethu, Niyathi Allu, Rohin Garg +2Machine Translation Low-Resource MT
Prediction Guard · Independent · Scale AI +1
Omnilingual MT: Machine Translation for 1,600 Languages
Mar 17, 2026Omnilingual MT Team, Belen Alastruey, Niyati Bafna +29Machine Translation Low-Resource MT
FAIR at Meta
Cross-Lingual Transfer and Parameter-Efficient Adaptation in the Turkic Language Family: A Theoretical Framework for Low-Resource Language Models
Mar 13, 2026O. Ibrahimzade, K. TabasaranskyCross-Lingual Transfer Multilingual Language Models
Learning from Child-Directed Speech in Two-Language Scenarios: A French-English Case Study
Mar 13, 2026Liel Binyamin, Elior SulemLanguage Model Pretraining Language Modeling
Faculty of Computer and Information Science, Institute for Applied AI Research Data Science Research Center Ben-Gurion University of the Negev
Just Use XML: Revisiting Joint Translation and Label Projection
Mar 12, 2026Thennal DK, Chris Biemann, Hans Ole HatzelCross-Lingual Transfer Low-Resource MT
Language Technology Group, University of Hamburg
Multi-lingual Multi-institutional Electronic Health Record based Predictive Model
Mar 11, 2026Kyunghoon Hur, Heeyoung Kwak, Jinsu Jang +2Electronic Health Records Cross-Lingual Transfer
Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea · NAVER Digital Healthcare LAB, Republic of Korea · Department of Health and Medical Information, Ansan University, Ansan-si, Gyeonggi-do 15328, Republic of Korea +1
Geometry-Aware Metric Learning for Cross-Lingual Few-Shot Sign Language Recognition on Static Hand Keypoints
Mar 10, 2026Chayanin Chamachot, Kanokphan LertniponphanSign Language Recognition Cross-Lingual Transfer
Department of Computer Engineering Faculty of Engineering, Chulalongkorn University
Quantifying Cross-Lingual Transfer in Paralinguistic Speech Tasks
Mar 9, 2026Pol Buitrago, Oriol Pareras, Federico Costa +1Speaker Verification Speech Processing
Barcelona Supercomputing Center (BSC), Spain · Universitat Polit`ecnica de Catalunya (UPC), Spain
Is continuous CoT better suited for multi-lingual reasoning?
Mar 9, 2026Ali Hamza Bashir, Behzad Shomali, Markus Frey +3Cross-Lingual Reasoning in Language Models CoT Reasoning
Lamarr Institute · Fraunhofer IAIS · University of Bonn
Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR
Mar 8, 2026Rishikesh Kumar Sharma, Safal Narshing Shrestha, Jenny Poudel +4Automatic Speech Recognition Low-Resource Language Processing
Information and Language Processing Research Lab, Kathmandu University
When Spoof Detectors Travel: Evaluation Across 66 Languages in the Low-Resource Language Spoofing Corpus
Mar 2, 2026Kirill Borodin, Vasiliy Kudryavtsev, Maxim Maslov +2Audio Deepfake Detection Speech Processing
lab260, Moscow Technical University of Communications and Informatics, Russia · BitmanagerAI, UAE
Effective QA-driven Annotation of Predicate-Argument Relations Across Languages
Feb 26, 2026Jonathan Davidov, Aviv Slobodkin, Shmuel Tomi Klein +3Semantic Parsing Cross-Lingual Transfer
Bar-Ilan University · Ariel University
Extending Czech Aspect-Based Sentiment Analysis with Opinion Terms: Dataset and LLM Benchmarks
Feb 26, 2026Jakub Šmíd, Pavel Přibáň, Pavel KrálAspect-Based Sentiment Analysis Low-Resource Language Processing
Department of Computer Science and Engineering, University of West Bohemia in Pilsen, Faculty of Applied Sciences, Univerzitní 2732/8, 301 00 Pilsen, Czech Republic · NTIS – New Technologies for the Information Society, University of West Bohemia in Pilsen, Faculty of Applied Sciences, Univerzitní 2732/8, 301 00 Pilsen, Czech Republic
Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads
Feb 25, 2026Shaswat Patel, Vishvesh Trivedi, Yue Han +2Multilingual Language Models Cross-Lingual Reasoning in Language Models
New York University
Evaluating Cross-Lingual Classification Approaches Enabling Topic Discovery for Multilingual Social Media Data
Feb 19, 2026Deepak Uniyal, Md Abul Bashar, Richi NayakCross-Lingual Transfer Social Media Analysis
Centre for Data Science, School of Computer Science, Queensland University of Technology, Brisbane, QLD 4000, Australia
When Semantic Overlap Is Not Enough: Cross-Lingual Euphemism Transfer Between Turkish and English
Feb 18, 2026Hasan Can Biyik, Libby Barak, Jing Peng +1Cross-Lingual Transfer Figurative Language Understanding
Montclair State University
BETA-Labeling for Multilingual Dataset Construction in Low-Resource IR
Feb 16, 2026Md. Najib Hasan, Mst. Jannatun Ferdous Rain, Fyad Mohammed +1Low-Resource Language Processing LLM-Assisted Annotation
Wichita State University · Begum Rokeya University, Rangpur · Khulna University of Engineering & Technology +1
Cross-Lingual Activation Steering for Multilingual Language Models
Jan 23, 2026Rhitabrat Pokharel, Ameeta Agrawal, Tanay NagarMultilingual Language Models Language Model Steering
Department of Computer Science, Portland State University, USA · Independent Researcher
Beyond Transfer Accuracy: Mechanism-Guided Controlled Adaptation for Low-Resource Languages
Jan 13, 2026Khumaisa Nur'aini, Ayu Purwarianti, Alham Fikri Aji +1Selective Fine-Tuning Circuit Discovery
Monash University Indonesia · MBZUAI · Institute Teknologi Bandung +1
What Matters When Building Universal Multilingual Named Entity Recognition Models?
Jan 9, 2026Jonas Golde, Patrick Haller, Alan AkbikNamed Entity Recognition Multilingual Language Models
Humboldt Universität zu Berlin
MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery
Dec 22, 2025Angelo Ortiz Tandazo, Manel Khentout, Youssef Benchekroun +2Speech Processing Self-Supervised Speech Representation Learning
ENS, PSL Research University, EHESS, CNRS, Paris, France · Meta AI Research, France · Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-lab, Grenoble, France
Mind the Gap... or Not? How Translation Errors and Evaluation Details Skew Multilingual Results
Nov 7, 2025Jan-Thorsten Peter, David Vilar, Tobias Domhan +2Mathematical Reasoning Benchmarks Multilingual Language Model Evaluation
Google
Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+
Oct 31, 2025Mason Shipton, York Hay Ng, Aditya Khan +4Low-Resource Language Processing Cross-Lingual Transfer
Ontario Tech University · University of Toronto · University of Michigan +1
Transferring Natural Language Datasets Between Languages Using Large Language Models for Modern Decision Support and Sci-Tech Analytical Systems
Oct 17, 2024Dmitrii Popov, Egor Terentev, Danil Serenko +2LLM-Assisted Annotation Low-Resource Language Processing
Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia · Faculty of Physics and Mathematics and Natural Sciences, RUDN University, Moscow 117198, Russia · Institute for Information Transmission Problems of the Russian Academy of Sciences (IITP RAS), Moscow 127051, Russia +1

Mar 19, 2026J/K move · Enter open · S save

Why Better Cross-Lingual Alignment Fails for Better Cross-Lingual Transfer: Case of Encoders

Yana Veitsman, Yihong Liu, Hinrich Schütze

University of Göttingen · LMU Munich · Munich Center for Machine Learning (MCML)

Cross-Lingual Representation Alignment Cross-Lingual Transfer Multilingual Language Models Gradient Interference

Open paper AskPDF arXiv

Cross-lingual alignment is often assumed to improve cross-lingual transfer by bringing representations of different languages closer together. However, improvements in representational alignment do not consistently translate into better downstream performance. We investigate this disconnect using XLM-R models explicitly aligned across four language pairs with token-level, sentence-level, and masked-language-modeling objectives. We evaluate their zero-shot transfer on a token-level task (part-of-speech tagging) and a sentence-level task (sentence classification), and analyze both representational changes and the gradients induced by the alignment and downstream objectives. We find that embedding-based alignment metrics do not reliably indicate whether alignment will improve or degrade downstream performance. Moreover, alignment and downstream-task gradients are often nearly orthogonal, particularly when the alignment objective and downstream task operate at different representational levels. These findings suggest that representation alignment alone is insufficient for assessing cross-lingual transfer, and that the compatibility between alignment and downstream objectives should be considered when designing/evaluating alignment methods.