{
 "id": "s-nlp/PsiloQA",
 "owner": "s-nlp",
 "name": "PsiloQA",
 "downloads": 310,
 "likes": 10,
 "last_modified": "2025-11-17T16:27:32.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "token-classification",
  "text-classification",
  "text-generation",
  "zero-shot-classification",
  "question-answering"
 ],
 "citation": "@inproceedings{rykov-etal-2025-models,\n    title = \"When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with {P}silo{QA}\",\n    author = \"Rykov, Elisei  and\n      Petrushina, Kseniia  and\n      Savkin, Maksim  and\n      Olisov, Valerii  and\n      Vazhentsev, Artem  and\n      Titova, Kseniia  and\n      Panchenko, Alexander  and\n      Konovalov, Vasily  and\n      Belikova, Julia\",\n    editor = \"Christodoulopoulos, Christos  and\n      Chakraborty, Tanmoy  and\n      Rose, Carolyn  and\n      Peng, Violet\",\n    booktitle = \"Findings of the Association for Computational Linguistics: EMNLP 2025\",\n    month = nov,\n    year = \"2025\",\n    address = \"Suzhou, China\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2025.findings-emnlp.626/\",\n    doi = \"10.18653/v1/2025.findings-emnlp.626\",\n    pages = \"11663--11682\",\n    ISBN = \"979-8-89176-335-7\",\n    abstract = \"Hallucination detection remains a fundamental challenge for the safe and reliable deployment of large language models (LLMs), especially in applications requiring factual accuracy. Existing hallucination benchmarks often operate at the sequence level and are limited to English, lacking the fine-grained, multilingual supervision needed for comprehensive evaluation. In this work, we introduce PsiloQA, a large-scale, multilingual dataset annotated with span-level hallucinations across 14 languages. PsiloQA is constructed through an automated three-stage pipeline:",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "375c3321b8331a689d664f77eb2753c6cdb17159",
 "stated_evidence": "https://huggingface.co/datasets/s-nlp/PsiloQA/blob/375c3321b8331a689d664f77eb2753c6cdb17159/README.md",
 "file_evidence": "https://huggingface.co/datasets/s-nlp/PsiloQA/tree/375c3321b8331a689d664f77eb2753c6cdb17159",
 "card_nc": false
}