{"url":"/task/pretrained-multilingual-language-models","name":"Pretrained Multilingual Language Models","slug":"pretrained-multilingual-language-models","description_markdown":null,"categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":26,"papers_with_code":12,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/belebele","name":"Belebele","full_name":"","num_papers_in_archive":68}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":12,"of":12,"tagged_in_all":26,"items":[{"url":"/paper/discovering-low-rank-subspaces-for-language","title":"Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations","date":"2024-01-11","arxiv_id":"2401.05792","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":8}},{"url":"/paper/improving-bilingual-lexicon-induction-with-1","title":"Improving Bilingual Lexicon Induction with Cross-Encoder Reranking","date":"2022-10-30","arxiv_id":"2210.16953","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/language-agnostic-multilingual-information","title":"Language Agnostic Multilingual Information Retrieval with Contrastive Learning","date":"2022-10-12","arxiv_id":"2210.06633","repositories_listed":1,"syntology":null},{"url":"/paper/are-pretrained-multilingual-models-equally-1","title":"Are Pretrained Multilingual Models Equally Fair Across Languages?","date":"2022-10-11","arxiv_id":"2210.05457","repositories_listed":1,"syntology":null},{"url":"/paper/robustification-of-multilingual-language","title":"Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining","date":"2022-10-10","arxiv_id":"2210.04782","repositories_listed":1,"syntology":null},{"url":"/paper/to-adapt-or-to-fine-tune-a-case-study-on","title":"To Adapt or to Fine-tune: A Case Study on Abstractive Summarization","date":"2022-08-30","arxiv_id":"2208.14559","repositories_listed":1,"syntology":null},{"url":"/paper/improving-word-translation-via-two-stage-1","title":"Improving Word Translation via Two-Stage Contrastive Learning","date":"2022-03-15","arxiv_id":"2203.08307","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/improving-word-translation-via-two-stage","title":"Improving Word Translation via Two-Stage Contrastive Learning","date":"2021-11-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/small-data-no-problem-exploring-the-viability","title":"Small Data? No Problem! Exploring the Viability of Pretrained Multilingual Language Models for Low-resourced Languages","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/specializing-multilingual-language-models-an","title":"Specializing Multilingual Language Models: An Empirical Study","date":"2021-06-16","arxiv_id":"2106.09063","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-math-word-problems-using","title":"Investigating Math Word Problems using Pretrained Multilingual Language Models","date":"2021-05-19","arxiv_id":"2105.08928","repositories_listed":1,"syntology":null},{"url":"/paper/how-good-is-your-tokenizer-on-the-monolingual","title":"How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models","date":"2020-12-31","arxiv_id":"2012.15613","repositories_listed":1,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}