{
 "id": "Intellexus/IdioLink",
 "owner": "Intellexus",
 "name": "IdioLink",
 "downloads": 210,
 "likes": 1,
 "last_modified": "2026-10-29T08:29:20.000Z",
 "stated_licence": "cc-by-nc-sa-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "text-retrieval"
 ],
 "citation": "@inproceedings{hashiloni-etal-2026-idiolink,\n    title = \"{I}dio{L}ink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions\",\n    author = \"Hashiloni, Kai Golan  and\n      Fadlon, Daniel  and\n      Livyatan, Lior  and\n      Shahar, Ofri Hefetz  and\n      Pei, Jiahuan  and\n      Bar, Kfir\",\n    editor = \"Lee, Hung-Yi  and\n      Dev, Sunipa  and\n      Li, Jessy  and\n      Elliott, Desmond\",\n    booktitle = \"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing\",\n    month = oct,\n    year = \"2026\",\n    address = \"Budapest, Hungary\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2026.emnlp-main.1912/\",\n    pages = \"43554--43573\",\n    ISBN = \"979-8-89176-459-0\",\n    abstract = \"Idioms pose a fundamental challenge for language models, as their meaning cannot be inferred from surface form alone. Understanding such expressions, therefore, requires semantic abstraction beyond lexical overlap. We introduce IdioLink, a retrieval benchmark designed to test whether models can link idiomatic expressions to conceptually equivalent meanings expressed in literal or paraphrased forms. IdioLink comprises 10,700 documents and 2,140 queries, spanning 107 idioms with both literal and figurative uses. Each document and query is annotated with spans that convey the core meaning. Evaluating strong embedding baselines (e.g., BGE, E5, Contriever, and Qwen), we show that current models struggle to re",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-sa-4.0) is classified as having use restrictions.",
 "revision": "21b2374b3b7dc99fda43169d85c4a17813f11039",
 "stated_evidence": "https://huggingface.co/datasets/Intellexus/IdioLink/blob/21b2374b3b7dc99fda43169d85c4a17813f11039/README.md",
 "file_evidence": "https://huggingface.co/datasets/Intellexus/IdioLink/tree/21b2374b3b7dc99fda43169d85c4a17813f11039",
 "card_nc": false
}