{"url":"/dataset/multi-eup","name":"Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval","full_name":null,"description_markdown":"The Multi-Eup is a new multilingual benchmark dataset, comprising 22K multilingual documents collected from the European Parliament, spanning 24 languages. This dataset is designed to investigate fairness in a multilingual information retrieval (IR) context to analyze both language and demographic bias in a ranking context. It boasts an authentic multilingual corpus, featuring topics translated into all 24 languages, as well as cross-lingual relevance judgments. Furthermore, it offers rich demographic information associated with its documents, facilitating the study of demographic bias.","description_withheld":null,"homepage":"https://github.com/jrnlp/Multi-EuP","introduced_date":"2023-11-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/multi-eup-the-multilingual-european","title":"Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval","first_author":"Jinrui Yang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Retrieval","url":"/task/text-retrieval","datasets_with_task":"/datasets/task/text-retrieval"},{"name":"Text Reranking","url":"/task/text-reranking","datasets_with_task":"/datasets/task/text-reranking"}],"languages":[],"variants":["Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}