{"url":"/task/cross-lingual-question-answering","name":"Cross-Lingual Question Answering","slug":"cross-lingual-question-answering","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"},{"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":25,"papers_with_code":12,"benchmarks":3,"benchmark_tables_in_archive":3,"benchmark_tables_shown":3,"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":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/cross-lingual-question-answering-on-tydiqa","slug":"cross-lingual-question-answering-on-tydiqa","dataset":"TyDiQA-GoldP","dataset_url":"/dataset/tydiqa-goldp","rows_in_archive":11,"metrics":["EM","F1"],"first_row_in_archive_order":{"model":"ByT5 (fine-tuned)","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-question-answering-on-xquad","slug":"cross-lingual-question-answering-on-xquad","dataset":"XQuAD","dataset_url":"/dataset/xquad","rows_in_archive":4,"metrics":["EM","F1","Average F1"],"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-question-answering-on-mlqa","slug":"cross-lingual-question-answering-on-mlqa","dataset":"MLQA","dataset_url":"/dataset/mlqa","rows_in_archive":3,"metrics":["F1","EM"],"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}}}],"datasets":[{"url":"/dataset/xquad","name":"XQuAD","full_name":"XQuAD","num_papers_in_archive":190},{"url":"/dataset/mlqa","name":"MLQA","full_name":"MultiLingual Question Answering","num_papers_in_archive":167},{"url":"/dataset/tydiqa-goldp","name":"TyDiQA-GoldP","full_name":"TyDiQA-GoldP","num_papers_in_archive":38},{"url":"/dataset/qald-9-plus","name":"QALD-9-Plus","full_name":"","num_papers_in_archive":3},{"url":"/dataset/litmind-dictionary","name":"LitMind Dictionary","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/question-answering","name":"Question Answering"}],"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":25,"items":[{"url":"/paper/scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","arxiv_id":"2210.11416","repositories_listed":9,"syntology":{"n":17,"n_ran":8,"n_unverified":9,"n_pointer_only":2}},{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":30,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/on-the-cross-lingual-transferability-of","title":"On the Cross-lingual Transferability of Monolingual Representations","date":"2019-10-25","arxiv_id":"1910.11856","repositories_listed":7,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"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/mluke-the-power-of-entity-representations-in","title":"mLUKE: The Power of Entity Representations in Multilingual Pretrained Language Models","date":"2021-10-15","arxiv_id":"2110.08151","repositories_listed":4,"syntology":null},{"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/indicgenbench-a-multilingual-benchmark-to","title":"IndicGenBench: A Multilingual Benchmark to Evaluate Generation Capabilities of LLMs on Indic Languages","date":"2024-04-25","arxiv_id":"2404.16816","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-cross-lingual-open-domain","title":"Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision","date":"2024-02-26","arxiv_id":"2402.16508","repositories_listed":1,"syntology":null},{"url":"/paper/promoting-generalized-cross-lingual-question","title":"Promoting Generalized Cross-lingual Question Answering in Few-resource Scenarios via Self-knowledge Distillation","date":"2023-09-29","arxiv_id":"2309.17134","repositories_listed":1,"syntology":null},{"url":"/paper/paxqa-generating-cross-lingual-question","title":"PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale","date":"2023-04-24","arxiv_id":"2304.12206","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-question-answering-over","title":"Cross-Lingual Question Answering over Knowledge Base as Reading Comprehension","date":"2023-02-26","arxiv_id":"2302.13241","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-data-augmentation-for-zero-shot","title":"Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering","date":"2020-10-23","arxiv_id":"2010.12643","repositories_listed":1,"syntology":null}],"syntology_records":4,"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"}}