{
 "id": "G4KMU/LEMUR",
 "owner": "G4KMU",
 "name": "LEMUR",
 "downloads": 40502,
 "likes": 5,
 "last_modified": "2026-03-31T16:41:34.000Z",
 "stated_licence": "apache-2.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@inproceedings{ahmadi-etal-2026-lemur,\n    title = \"{LEMUR}: A Corpus for Robust Fine-Tuning of Multilingual Law Embedding Models for Retrieval\",\n    author = \"Ahmadi, Narges Baba  and\n      Strich, Jan  and\n      Semmann, Martin  and\n      Biemann, Chris\",\n    editor = \"Baez Santamaria, Selene  and\n      Somayajula, Sai Ashish  and\n      Yamaguchi, Atsuki\",\n    booktitle = \"Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)\",\n    month = mar,\n    year = \"2026\",\n    address = \"Rabat, Morocco\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.eacl-srw.18/\",\n    doi = \"10.18653/v1/2026.eacl-srw.18\",\n    pages = \"248--265\",\n    ISBN = \"979-8-89176-383-8\",\n    abstract = \"Large language models (LLMs) are increasingly used to access legal information. Yet, their deployment in multilingual legal settings is constrained by unreliable retrieval and the lack of domain-adapted, open-embedding models. In particular, existing multilingual legal corpora are not designed for semantic retrieval, and PDF-based legislative sources introduce substantial noise due to imperfect text extraction. To address these challenges, we introduce LEMUR, a large-scale multilingual corpus of EU environmental legislation constructed from 24,953 official EUR-Lex PDF documents covering 25 languages. We further propose the Lexical Content Score (LCS), a langu",
 "signal": "permissive",
 "reason": "The declared licence (apache-2.0) is classified as permissive."
}