{"url":"/method/xlm-r","slug":"xlm-r","name":"XLM-R","full_name":"XLM-R","full_name_withheld":false,"description_markdown":"XLM-R","description_state":"present","introduced_year":null,"introduced_by":{"title":"Unsupervised Cross-lingual Representation Learning at Scale","paper":"/paper/unsupervised-cross-lingual-representation-1","first_author":"Alexis Conneau","n_authors":10,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/unsupervised-cross-lingual-representation-1"},"source":{"url":"https://arxiv.org/abs/1911.02116v2","title":"Unsupervised Cross-lingual Representation Learning at Scale","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Language Models","url":"/methods/category/language-models","pwc_aliases":[]}],"n_papers_tagged":176,"archive_num_papers":176,"papers_newest_first":[{"paper":"/paper/multilingual-encoder-knows-more-than-you","title":"Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource Languages","date":"2025-02-15","arxiv_id":"2502.10852","n_code_links":1,"syntology":null},{"paper":null,"title":"AmaSQuAD: A Benchmark for Amharic Extractive Question Answering","date":"2025-02-04","arxiv_id":"2502.02047","n_code_links":0,"syntology":null},{"paper":null,"title":"Evaluating the Effectiveness of XAI Techniques for Encoder-Based Language Models","date":"2025-01-26","arxiv_id":"2501.15374","n_code_links":0,"syntology":null},{"paper":null,"title":"Comparative Approaches to Sentiment Analysis Using Datasets in Major European and Arabic Languages","date":"2025-01-21","arxiv_id":"2501.12540","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","date":"2025-01-17","arxiv_id":"2501.10175","n_code_links":0,"syntology":null},{"paper":null,"title":"BabyLMs for isiXhosa: Data-Efficient Language Modelling in a Low-Resource Context","date":"2025-01-07","arxiv_id":"2501.03855","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-applicability-of-zero-shot-cross","title":"On the Applicability of Zero-Shot Cross-Lingual Transfer Learning for Sentiment Classification in Distant Language Pairs","date":"2024-12-24","arxiv_id":"2412.18188","n_code_links":1,"syntology":null},{"paper":null,"title":"Retrofitting Large Language Models with Dynamic Tokenization","date":"2024-11-27","arxiv_id":"2411.18553","n_code_links":0,"syntology":null},{"paper":null,"title":"Transformer-Based Contextualized Language Models Joint with Neural Networks for Natural Language Inference in Vietnamese","date":"2024-11-20","arxiv_id":"2411.13407","n_code_links":0,"syntology":null},{"paper":"/paper/langsamp-language-script-aware-multilingual","title":"LangSAMP: Language-Script Aware Multilingual Pretraining","date":"2024-09-26","arxiv_id":"2409.18199","n_code_links":1,"syntology":null},{"paper":"/paper/lowrem-a-repository-of-word-embeddings-for-87","title":"GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge","date":"2024-09-26","arxiv_id":"2409.18193","n_code_links":1,"syntology":null},{"paper":"/paper/mgte-generalized-long-context-text","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","date":"2024-07-29","arxiv_id":"2407.19669","n_code_links":0,"syntology":{"ran":1,"of":1,"unverified":0,"pointer_only":1}},{"paper":null,"title":"The Model Arena for Cross-lingual Sentiment Analysis: A Comparative Study in the Era of Large Language Models","date":"2024-06-27","arxiv_id":"2406.19358","n_code_links":0,"syntology":null},{"paper":"/paper/medical-spoken-named-entity-recognition","title":"Medical Spoken Named Entity Recognition","date":"2024-06-19","arxiv_id":"2406.13337","n_code_links":1,"syntology":null},{"paper":null,"title":"Targeted Multilingual Adaptation for Low-resource Language Families","date":"2024-05-20","arxiv_id":"2405.12413","n_code_links":0,"syntology":null},{"paper":null,"title":"Adapting Mental Health Prediction Tasks for Cross-lingual Learning via Meta-Training and In-context Learning with Large Language Model","date":"2024-04-13","arxiv_id":"2404.09045","n_code_links":0,"syntology":null},{"paper":null,"title":"MaiNLP at SemEval-2024 Task 1: Analyzing Source Language Selection in Cross-Lingual Textual Relatedness","date":"2024-04-03","arxiv_id":"2404.02570","n_code_links":0,"syntology":null},{"paper":"/paper/cicle-conformal-in-context-learning-for","title":"CICLe: Conformal In-Context Learning for Largescale Multi-Class Food Risk Classification","date":"2024-03-18","arxiv_id":"2403.11904","n_code_links":1,"syntology":null},{"paper":null,"title":"Machines Do See Color: A Guideline to Classify Different Forms of Racist Discourse in Large Corpora","date":"2024-01-17","arxiv_id":"2401.09333","n_code_links":0,"syntology":null},{"paper":null,"title":"LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization","date":"2024-01-11","arxiv_id":"2401.06034","n_code_links":0,"syntology":null},{"paper":null,"title":"Hate Speech and Offensive Content Detection in Indo-Aryan Languages: A Battle of LSTM and Transformers","date":"2023-12-09","arxiv_id":"2312.05671","n_code_links":0,"syntology":null},{"paper":null,"title":"A Text-to-Text Model for Multilingual Offensive Language Identification","date":"2023-12-06","arxiv_id":"2312.03379","n_code_links":0,"syntology":null},{"paper":"/paper/kbioxlm-a-knowledge-anchored-biomedical","title":"KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model","date":"2023-11-20","arxiv_id":"2311.11564","n_code_links":1,"syntology":null},{"paper":"/paper/mela-multilingual-evaluation-of-linguistic","title":"MELA: Multilingual Evaluation of Linguistic Acceptability","date":"2023-11-15","arxiv_id":"2311.09033","n_code_links":1,"syntology":null},{"paper":"/paper/calamancy-a-tagalog-natural-language","title":"calamanCy: A Tagalog Natural Language Processing Toolkit","date":"2023-11-13","arxiv_id":"2311.07171","n_code_links":1,"syntology":null},{"paper":null,"title":"Zero-Shot Cross-Lingual Sentiment Classification under Distribution Shift: an Exploratory Study","date":"2023-11-11","arxiv_id":"2311.06549","n_code_links":0,"syntology":null},{"paper":"/paper/improving-cross-lingual-transfer-through","title":"Improving Cross-Lingual Transfer through Subtree-Aware Word Reordering","date":"2023-10-20","arxiv_id":"2310.13583","n_code_links":1,"syntology":null},{"paper":null,"title":"MedAI Dialog Corpus (MEDIC): Zero-Shot Classification of Doctor and AI Responses in Health Consultations","date":"2023-10-19","arxiv_id":"2310.12489","n_code_links":0,"syntology":null},{"paper":"/paper/visobert-a-pre-trained-language-model-for","title":"ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing","date":"2023-10-17","arxiv_id":"2310.11166","n_code_links":1,"syntology":null},{"paper":"/paper/qasina-religious-domain-question-answering","title":"QASiNa: Religious Domain Question Answering using Sirah Nabawiyah","date":"2023-10-12","arxiv_id":"2310.08102","n_code_links":1,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/xlm-r","name":"XLM-R","papers":174},{"task":"/task/language-modelling","name":"Language Modelling","papers":40},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":34},{"task":"/task/language-modeling","name":"Language Modeling","papers":31},{"task":"/task/sentence","name":"Sentence","papers":25},{"task":"/task/text-classification","name":"Text Classification","papers":17},{"task":"/task/text-classification-1","name":"text-classification","papers":17},{"task":"/task/cg","name":"NER","papers":16},{"task":"/task/natural-language-inference","name":"Natural Language Inference","papers":14},{"task":"/task/zero-shot-cross-lingual-transfer","name":"Zero-Shot Cross-Lingual Transfer","papers":14},{"task":"/task/classification-1","name":"Classification","papers":13},{"task":"/task/named-entity-recognition-1","name":"Named Entity Recognition","papers":13},{"task":"/task/named-entity-recognition-ner","name":"Named Entity Recognition (NER)","papers":13},{"task":"/task/named-entity-recognition","name":"named-entity-recognition","papers":13},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":12},{"task":"/task/question-answering","name":"Question Answering","papers":11},{"task":"/task/sentiment-analysis","name":"Sentiment Analysis","papers":11},{"task":"/task/machine-translation","name":"Machine Translation","papers":10},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":10},{"task":"/task/retrieval","name":"Retrieval","papers":10}],"tasks_shown":20,"n_tasks":179,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":18},{"year":"2021","papers":52},{"year":"2022","papers":55},{"year":"2023","papers":30},{"year":"2024","papers":14},{"year":"2025","papers":6}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/xlm-r"},"syntology_read_at":"2026-09-25T09:33:49+00:00"}