{"url":"/task/cross-lingual-paraphrase-identification","name":"Cross-Lingual Paraphrase Identification","slug":"cross-lingual-paraphrase-identification","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6,"papers_with_code":5,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/paws-x","name":"PAWS-X","full_name":"PAWS-X","num_papers_in_archive":172},{"url":"/dataset/sv-ident","name":"SV-Ident","full_name":"Survey Variable Identification","num_papers_in_archive":4}],"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":5,"of":5,"tagged_in_all":6,"items":[{"url":"/paper/byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","arxiv_id":"2105.13626","repositories_listed":5,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","arxiv_id":"2010.12821","repositories_listed":4,"syntology":null},{"url":"/paper/do-multilingual-language-models-think-better","title":"Do Multilingual Language Models Think Better in English?","date":"2023-08-02","arxiv_id":"2308.01223","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/promptbench-towards-evaluating-the-robustness","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","date":"2023-06-07","arxiv_id":"2306.04528","repositories_listed":1,"syntology":null},{"url":"/paper/mgpt-few-shot-learners-go-multilingual","title":"mGPT: Few-Shot Learners Go Multilingual","date":"2022-04-15","arxiv_id":"2204.07580","repositories_listed":1,"syntology":null}],"syntology_records":2,"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"}}