Cross-Lingual Representation Alignment

Follow this topic Ask about this topic

The field studies how words, sentences, and internal model features in different languages correspond, enabling knowledge and task performance to transfer across languages. Common approaches use parallel-text contrastive learning, mapping or optimal-transport methods, and inference-time interventions; researchers also probe whether shared structure emerges without joint training. Applications include multilingual retrieval, reasoning, safety, speech, and multimodal tasks, especially for low-resource languages. A central tension is that greater geometric alignment does not always improve downstream transfer, and models must share meaning without erasing differences in language, script, or culture.

Latest papers

68 papers16 papers in the last four weeks, up 78% on the four weeks before. 0.1% of all new papers.

Where meanings converge and diverge: Revisiting linguistic relativity across 81 languages
Oct 22, 2026Weiran Wang, Wenjuan Qin, Haitao LiuSemantic Correspondence Cross-Lingual Representation Alignment
Fudan University, Shanghai 200433, China
Scaling Multilingual Pretraining of Pixel Language Models
Oct 21, 2026Ilker Kesen, Jenny Kunz, Kasra Malihi +1Multilingual Language Models Language Model Scaling
Humboldt-Universität zu Berlin · Linköping University · University of Copenhagen
From Unverifiable Domain Text to Cross-Lingual RLVR via Code-Switched Task Synthesis
Oct 18, 2026Cheonbok Park, Jihwan Kim, Shinyoung Joo +4Cross-Lingual Transfer Code-Switching
NAVER Cloud · KAIST AI
Multilingual Brain Decoding Reveals Shared Cortical Semantic Geometry
Oct 17, 2026Yi Guo, Yong Hu, Michael Kwok-Po Ng +1Cross-Lingual Representation Alignment Neural Representation Geometry
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China. · University of Chinese Academy of Sciences, Beijing, China. · The University of Hong Kong, Hong Kong, China. +1
Steering beyond Language: Improving Multilingual Training-Free Text Embeddings via Paired-Residual Subspace Removal
Oct 16, 2026Ailiang Lin, Zhuoyun Li, Yusong Wang +3Text Embeddings Cross-Lingual Representation Alignment
Institute of Science Tokyo · Tencent
Probing the Geometry of Color Representations in Multilingual Language Models
Oct 13, 2026Pablo Loyola, Edison Marrese-Taylor, Andrés Hoyos-IdroboRepresentation Geometry in Language Models Multilingual Language Models
Rakuten Group, Inc. · Graduate School of Engineering, The University of Tokyo, Japan
Cross-Lingual Transfer of Evil Vectors Is Directionally Asymmetric
Oct 13, 2026Juann Kim, Minku KangCross-Lingual Transfer Activation Steering
University of Southern California · KAIST
Language Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark Evaluation
Oct 6, 2026Shu-Kai Hsieh, Da-Chen LianCultural Knowledge in Language Models LLM Evaluation
National Taiwan University
A theory of platonic representations in language models
Oct 5, 2026Darshil Doshi, Wenjie Zhou, Corinna Elena Wegner +3Belief Propagation Multilingual Language Models
Johns Hopkins Univeristy · Johns Hopkins University & EPFL
Introducing Code-Switched Contexts to Cognitively-Inspired Bilingual Model Training
Oct 5, 2026Zhuojing Huang, Luise Pohlmann, Lisa BeinbornLanguage Model Pretraining Multilingual Language Models
University of Göttingen, Germany
Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII
Oct 5, 2026Alexandru Nazare, Agnese Profico, Nicolò Vania +6Multilingual Language Models Cross-Lingual Representation Alignment
Human-Centric ART, University of Rome Tor Vergata · Department of Computer Science, University of Luxembourg · Almawave Labs, Rome
Cross-Lingual Alignment for Decoder-Only Models using MoE Routers
Oct 1, 2026Lucas Bandarkar, Clark Peng, Ahmed Haj Ahmed +2Mixture-of-Experts Language Models Cross-Lingual Representation Alignment
University of California, Los Angeles∗ · Haverford College · MILA - Quebec AI Institute & McGill University
Beyond Linear Concepts: Discovering and Aligning Non-Linear Concept Manifolds in Large Language Models
Oct 1, 2026Tido Specht, Elias Benedict Krey, Nils Neukirch +1LLM Alignment LLM Interpretability
University of Groningen · Carl von Ossietzky University of Oldenburg
Do Multilingual Encoders Produce Language-Consistent Semantic IDs?
Oct 1, 2026Abhinav Bohra, Anuj BohraMultilingual Language Model Evaluation Semantic ID Recommendation
Rutgers University
Geometric Representations of African Languages: A Regional Semantic Hub and Cultural Steering
Sep 28, 2026Muhammad Abdullahi Said, Jonathan ShockAfrican Language Processing Representation Geometry in Language Models
African Institute for Mathematical Sciences (AIMS) · University of Cape Town (UCT)
Multilinguality in Hybrid Attention LLMs
Sep 28, 2026Lucas Bandarkar, Junlin Hu, Chenyuan Yang +2Multilingual Language Models Cross-Lingual Representation Alignment
University of California, Los Angeles · Fudan University
Feeding BabyLMs Macaroni: Code-Switching Curricula Cause Cross-Lingual Convergence
Sep 24, 2026Dries Rooryck, Alex Cai, Yonatan Belinkov +2Multilingual Language Models Language Model Pretraining
Kempner Institute, Harvard University, Cambridge, MA, USA · Technion – Israel Institute of Technology, Haifa, Israel
Rethinking Pivot Programming Languages in Code Language Models
Sep 19, 2026Andor Diera, Lukas Galke Poech, Matthias TichyCode Language Models Cross-Lingual Transfer
Ulm University Ulm, Germany · University of Southern Denmark Odense, Denmark
A Cross-Lingual Acoustic Disease-Alignment Framework for Respiratory Health Assessment from Spontaneous Speech
Sep 16, 2026Roksana Khanom, Raghib Asfak Tasnim, Bodrun Nahar Bithi +4Cross-Lingual Representation Alignment Speech Processing
University of Maryland, College Park, USA · Sylhet MAG Osmani Medical College Hospital, Bangladesh · Dr. M R Khan Shishu Hospital & Institute of Child Health, Bangladesh +1
Right Tool, Right Job: Native-Language Evaluation, Tokenizer Sensitivity, and Methodological Findings from a French-Only BabyLM
Sep 15, 2026Adam Zachary Wasserman, David BeaucheminLLM Evaluation Cross-Lingual Representation Alignment
1Open Honest Foundation · 2Group for Research in Artificial Intelligence of Laval University (GRAIL), Université Laval, Québec, Canada
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
Improving Cross-Lingual Token Representations by Adding a Pinch of SALT
Sep 9, 2026Guillem RamírezSentence Embeddings Cross-Lingual Representation Alignment
ILCC, University of Edinburgh
Cross-Lingual Representation Alignment by Token-Level Optimal Transport in a Language-Agnostic Space
Sep 6, 2026Taisei Yamamoto, Ryoma Kumon, Danushka Bollegala +1Cross-Lingual Representation Alignment Cross-Lingual Consistency in Language Models
The University of Tokyo · Riken · University of Liverpool +1
A Systematic Comparison of Multilingual Interpretability Methods Reveals Anisotropy-Driven Failures
Sep 4, 2026Oskar Holmström, Marcel Bollmann, Marco KuhlmannCross-Lingual Representation Alignment Multilingual Language Models
Linköping University
Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?
Aug 31, 2026Donghoon Han, SungHyun Moon, Aidyn Zhakatayev +2Cross-Lingual Representation Alignment Multilingual VLM Evaluation
Dnotitia Inc.
Latent-Space Intervention for Cross-Lingual Factual Consistency: Consistency Improvements without Accuracy Drops
Aug 28, 2026Faeze Ghorbanpour, Constanza Fierro, Alexander Fraser +1Cross-Lingual Consistency in Language Models Multilingual QA
School of Computation, Information and Technology, TU Munich · Munich Center for Machine Learning (MCML) · Department of Computer Science, University of Copenhagen
Unsupervised Latent Space Alignment with Hyperspherical Geodesic Matching
Aug 28, 2026Cameron Ryan, Vivek Sivaraman Narayanaswamy, Kowshik Thopalli +1Latent Space Alignment Latent Space Geometry
Northeastern University, Boston, MA 02115. Work performed during a summer internship at Lawrence Livermore National Laboratory · Lawrence Livermore National Laboratory, Livermore, CA 94551-0808.
Cross-Lingual Alignment Without Joint Training: Do Monolingual Language Models Converge on Universal Representations?
Aug 27, 2026Ej Zhou, Suchir Salhan, Catherine Arnett +1Cross-Lingual Representation Alignment Language Modeling
University of Cambridge · EleutherAI
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
Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders
Aug 24, 2026Igor Bogdanov, Changcheng HuangCross-Lingual Reasoning in Language Models Cross-Lingual Representation Alignment
Department of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canada.

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

Where meanings converge and diverge: Revisiting linguistic relativity across 81 languages

Weiran Wang, Wenjuan Qin, Haitao Liu

Fudan University, Shanghai 200433, China

Semantic Correspondence Cross-Lingual Representation Alignment

Open paper AskPDF arXiv

Do people who speak different languages organize concepts in similar ways? This question lies at the heart of the Sapir--Whorf hypothesis and debates about linguistic relativity. Shared basic meanings, however, need not imply shared relations among them. We compared relations among 196 basic concepts across 81 languages, using word embeddings from two multilingual models to quantify conceptual structure expressed in language. Cross-language correspondence was greater for sociocultural meanings than for meanings concerning nature and motion, a contrast recurring across models and classifications. Within the sociocultural domain, relational differences increased with geographic separation; less closely related languages differed more across all domains. These findings suggest that universality and relativity are interwoven across conceptual domains. They inform an account in which shared cognitive resources interact with linguistic and local experience, and predict greater cross-language correspondence in human semantic judgments for sociocultural than for nature and motion meanings.