{
 "id": "tresiwalde/lou",
 "owner": "tresiwalde",
 "name": "lou",
 "downloads": 40,
 "likes": 1,
 "last_modified": "2024-11-16T22:37:13.000Z",
 "stated_licence": "cc-by-nc-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@inproceedings{waldis-etal-2024-lou,\n    title = \"The {L}ou Dataset - Exploring the Impact of Gender-Fair Language in {G}erman Text Classification\",\n    author = \"Waldis, Andreas  and\n      Birrer, Joel  and\n      Lauscher, Anne  and\n      Gurevych, Iryna\",\n    editor = \"Al-Onaizan, Yaser  and\n      Bansal, Mohit  and\n      Chen, Yun-Nung\",\n    booktitle = \"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing\",\n    month = nov,\n    year = \"2024\",\n    address = \"Miami, Florida, USA\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://aclanthology.org/2024.emnlp-main.592\",\n    pages = \"10604--10624\",\n    abstract = \"Gender-fair language, an evolving linguistic variation in German, fosters inclusion by addressing all genders or using neutral forms. However, there is a notable lack of resources to assess the impact of this language shift on language models (LMs) might not been trained on examples of this variation. Addressing this gap, we present Lou, the first dataset providing high-quality reformulations for German text classification covering seven tasks, like stance detection and toxicity classification. We evaluate 16 mono- and multi-lingual LMs and find substantial label flips, reduced prediction certainty, and significantly altered attention patterns. However, existing evaluations remain valid, as LM rankings are consistent across original and reformulated instances. Our study provides initial insights into the",
 "signal": "restrictive",
 "reason": "The declared licence (cc-by-nc-4.0) is classified as having use restrictions.",
 "revision": "4d4f1f017593e82f4915ba9680ea3887e2da8076",
 "stated_evidence": "https://huggingface.co/datasets/tresiwalde/lou/blob/4d4f1f017593e82f4915ba9680ea3887e2da8076/README.md",
 "file_evidence": "https://huggingface.co/datasets/tresiwalde/lou/tree/4d4f1f017593e82f4915ba9680ea3887e2da8076",
 "card_nc": false
}