{"url":"/task/cross-lingual-natural-language-inference","name":"Cross-Lingual Natural Language Inference","slug":"cross-lingual-natural-language-inference","description_markdown":"Using data and models available for one language for which ample such resources are available (e.g., English) to solve a natural language inference task in another, commonly more low-resource, language.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":31,"papers_with_code":17,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":1},"benchmarks":[{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-4","slug":"cross-lingual-natural-language-inference-on-4","dataset":"XNLI","dataset_url":"/dataset/xnli","rows_in_archive":5,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"ByT5 XXL","paper_title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","paper_url":"/paper/byt5-towards-a-token-free-future-with-pre","paper_date":"2021-05-28","arxiv_id":"2105.13626","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers/tree/master/src/transformers/models/byt5"},{"title":"google-research/byt5","url":"https://github.com/google-research/byt5"},{"title":"ufal/multilexnorm2021","url":"https://github.com/ufal/multilexnorm2021"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/byt5"},{"title":"yoreG123/Paddle-ByT5","url":"https://github.com/yoreG123/Paddle-ByT5"}],"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}}},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-1","slug":"cross-lingual-natural-language-inference-on-1","dataset":"XNLI Zero-Shot English-to-Spanish","dataset_url":"/dataset/xnli","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"XLM-R R4F","paper_title":"Better Fine-Tuning by Reducing Representational Collapse","paper_url":"/paper/better-fine-tuning-by-reducing","paper_date":"2020-08-06","arxiv_id":"2008.03156","code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/rxf"},{"title":"cosmoquester/2021-dialogue-summary-competition","url":"https://github.com/cosmoquester/2021-dialogue-summary-competition"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"}],"syntology":null}},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on-3","slug":"cross-lingual-natural-language-inference-on-3","dataset":"XNLI Zero-Shot English-to-German","dataset_url":"/dataset/xnli","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"XLM-R R4F","paper_title":"Better Fine-Tuning by Reducing Representational Collapse","paper_url":"/paper/better-fine-tuning-by-reducing","paper_date":"2020-08-06","arxiv_id":"2008.03156","code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/rxf"},{"title":"cosmoquester/2021-dialogue-summary-competition","url":"https://github.com/cosmoquester/2021-dialogue-summary-competition"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"}],"syntology":null}},{"leaderboard":"/sota/cross-lingual-natural-language-inference-on","slug":"cross-lingual-natural-language-inference-on","dataset":"XNLI Zero-Shot English-to-French","dataset_url":"/dataset/xnli","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"XLM-R R4F","paper_title":"Better Fine-Tuning by Reducing Representational Collapse","paper_url":"/paper/better-fine-tuning-by-reducing","paper_date":"2020-08-06","arxiv_id":"2008.03156","code_links":[{"title":"pytorch/fairseq","url":"https://github.com/pytorch/fairseq/tree/master/examples/rxf"},{"title":"cosmoquester/2021-dialogue-summary-competition","url":"https://github.com/cosmoquester/2021-dialogue-summary-competition"},{"title":"cliang1453/camero","url":"https://github.com/cliang1453/camero"}],"syntology":null}}],"datasets":[{"url":"/dataset/xnli","name":"XNLI","full_name":"Cross-lingual Natural Language Inference","num_papers_in_archive":349},{"url":"/dataset/xglue","name":"XGLUE","full_name":"","num_papers_in_archive":22}],"subtasks":[],"parent_tasks":[{"url":"/task/natural-language-inference","name":"Natural Language Inference"}],"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":17,"of":17,"tagged_in_all":31,"items":[{"url":"/paper/bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","repositories_listed":534,"syntology":{"n":659,"n_ran":204,"n_unverified":455,"n_pointer_only":149}},{"url":"/paper/supervised-learning-of-universal-sentence","title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","date":"2017-05-05","arxiv_id":"1705.02364","repositories_listed":23,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":7}},{"url":"/paper/massively-multilingual-sentence-embeddings","title":"Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond","date":"2018-12-26","arxiv_id":"1812.10464","repositories_listed":13,"syntology":{"n":10,"n_ran":4,"n_unverified":6,"n_pointer_only":4}},{"url":"/paper/xnli-evaluating-cross-lingual-sentence","title":"XNLI: Evaluating Cross-lingual Sentence Representations","date":"2018-09-13","arxiv_id":"1809.05053","repositories_listed":9,"syntology":null},{"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/better-fine-tuning-by-reducing","title":"Better Fine-Tuning by Reducing Representational Collapse","date":"2020-08-06","arxiv_id":"2008.03156","repositories_listed":3,"syntology":null},{"url":"/paper/2408-00675","title":"Leveraging Entailment Judgements in Cross-Lingual Summarisation","date":"2024-08-01","arxiv_id":"2408.00675","repositories_listed":1,"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/enhancing-cross-lingual-natural-language-1","title":"Enhancing Cross-lingual Natural Language Inference by Soft Prompting with Multilingual Verbalizer","date":"2023-05-22","arxiv_id":"2305.12761","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/nebula-i-a-general-framework-for","title":"Nebula-I: A General Framework for Collaboratively Training Deep Learning Models on Low-Bandwidth Cloud Clusters","date":"2022-05-19","arxiv_id":"2205.09470","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-cross-lingual-natural-language","title":"Enhancing Cross-lingual Natural Language Inference by Prompt-learning from Cross-lingual Templates","date":"2022-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/bridging-cross-lingual-gaps-during-leveraging","title":"Bridging Cross-Lingual Gaps During Leveraging the Multilingual Sequence-to-Sequence Pretraining for Text Generation and Understanding","date":"2022-04-16","arxiv_id":"2204.07834","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},{"url":"/paper/subword-mapping-and-anchoring-across","title":"Subword Mapping and Anchoring across Languages","date":"2021-09-09","arxiv_id":"2109.04556","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/paradise-exploiting-parallel-data-for","title":"PARADISE: Exploiting Parallel Data for Multilingual Sequence-to-Sequence Pretraining","date":"2021-08-04","arxiv_id":"2108.01887","repositories_listed":1,"syntology":null},{"url":"/paper/language-embeddings-for-typology-and-cross","title":"Language Embeddings for Typology and Cross-lingual Transfer Learning","date":"2021-06-03","arxiv_id":"2106.02082","repositories_listed":1,"syntology":null}],"syntology_records":7,"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"}}