{
 "id": "llm-jp/AnswerCarefully",
 "owner": "llm-jp",
 "name": "AnswerCarefully",
 "downloads": 852,
 "likes": 191,
 "last_modified": "2026-08-20T01:02:50.000Z",
 "stated_licence": "other",
 "stated_from": "tag",
 "licence_name": "answer-carefully-dataset-tou",
 "licence_link": "LICENSE",
 "file_licence": null,
 "licence_files": [
  "LICENSE",
  "LICENSE_ja"
 ],
 "sources": [],
 "gated": "manual",
 "tasks": [],
 "citation": "@inproceedings{suzuki-etal-2026-answercarefully,\n  title = {AnswerCarefully: Creating a Dataset for LLM Safety in Japanese},\n  author = {Suzuki, Hisami and Katsumata, Satoru and Kodama, Takashi and Takahashi, Tetsuro and Nakayama, Kouta and Sekine, Satoshi},\n  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026)},\n  month = {May},\n  year = {2026},\n  pages = {3921--3931},\n  address = {Palma, Mallorca, Spain},\n  publisher = {European Language Resources Association (ELRA)},\n  editor = {Piperidis, Stelios and Bel, Núria and van den Heuvel, Henk and Ide, Nancy and Krek, Simon and Toral, Antonio},\n  doi = {10.63317/289xxmwcworn},\n  abstract = {In this paper we present JLLMSafety, a dataset for promoting the safety of Japanese LLM outputs. The dataset consists of 1,800 pairs of questions and reference answers, where the questions require special attention in answering. It covers a wide range of risk categories established in prior English-language datasets, but the data samples are original in that they are manually curated to reflect the socio-cultural context of LLM usage in Japan. We show that using this dataset for instruction to fine-tune a Japanese LLM led to improved output safety without compromising the utility of general responses. We also report the results of a safety evaluation of 12 Japanese LLMs using this dataset as a benchmark. Finally, we discuss the significance of creating regionally specific datasets of LLM safety, a",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "d1d4e57cd4d7aecb44f879e7488832011fcaddb0",
 "stated_evidence": "https://huggingface.co/datasets/llm-jp/AnswerCarefully/blob/d1d4e57cd4d7aecb44f879e7488832011fcaddb0/README.md",
 "file_evidence": "https://huggingface.co/datasets/llm-jp/AnswerCarefully/blob/d1d4e57cd4d7aecb44f879e7488832011fcaddb0/LICENSE",
 "card_nc": false
}