{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T08:50:54Z","timestamp":1781772654478,"version":"3.54.5"},"reference-count":10,"publisher":"China Science Publishing & Media Ltd.","issue":"2","content-domain":{"domain":["engine.scichina.com"],"crossmark-restriction":false},"short-container-title":["DI"],"published-print":{"date-parts":[[2026,6,1]]},"DOI":"10.3724\/2096-7004.di.2025.0044","type":"journal-article","created":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T08:11:42Z","timestamp":1780906302000},"page":"20250044","update-policy":"https:\/\/doi.org\/10.1360\/scp-crossmark-policy-page","source":"Crossref","is-referenced-by-count":0,"title":["Dataset Used for Reinforcement Learning Tasks of Tibetan Large Models"],"prefix":"10.3724","volume":"8","author":[{"given":"Long","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gengga","family":"Duojie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2026","published-online":{"date-parts":[[2026,6,8]]},"reference":[{"key":"null","unstructured":"Zhao W. X. et al., \u201cA survey of large language models,\u201d arXiv preprint, arXiv:2303.18223, 2023."},{"key":"null","unstructured":"Peng B., Li C., He P., Galley M., and Gao J., \u201cInstruction tuning with GPT-4,\u201d arXiv preprint, arXiv:2304.03277, 2023."},{"key":"null","unstructured":"Touvron H. et al., \u201cLlama 2: Open foundation and fine-tuned chat models,\u201d arXiv preprint, arXiv:2307.09288, 2023."},{"key":"null","unstructured":"Yang A. et al., \u201cBaichuan 2: Open large-scale language models,\u201d arXiv preprint, arXiv:2309.10305, 2023."},{"key":"null","unstructured":"Ji J. et al., \u201cBeaverTails: Towards improved safety alignment of LLM via a human-preference dataset,\u201d in Adv. Neural Inf. Process. Syst., vol. 36, 2023, pp. 24678\u201324704."},{"key":"null","unstructured":"Cao Y., Sheng Q. Z., McAuley J., and Yao L., \u201cReinforcement learning for generative AI: A survey,\u201d arXiv preprint, arXiv:2308.14328, 2023."},{"key":"null","unstructured":"Lee H. et al., \u201cRLAF: Scaling reinforcement learning from human feedback with AI feedback,\u201d arXiv preprint, arXiv:2309.00209, 2023."},{"key":"null","unstructured":"Le Scao T. et al., \u201cBLOOM: A 176B-parameter open-access multilingual language model,\u201d 2023."},{"key":"null","unstructured":"Bai Y. et al., \u201cTraining a helpful and harmless assistant with reinforcement learning from human feedback,\u201d arXiv preprint, arXiv:2204.05862, 2022."},{"key":"null","unstructured":"Thakkar M., Bolukbasi T., Ganapathy S., Vashishth S., Chandar S., and Talukdar P., \u201cSelf-influence guided data reweighting for language model pre-training,\u201d in Proc. 2023 Conf. Empir. Methods Natural Lang. Process. (EMNLP), 2023, pp. 2033\u20132045."}],"container-title":["Data Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/818B98CE8FD144A18F6EEEC567B7EE92","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0044","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.sciengine.com\/sci-open\/api\/v1\/open\/file\/pdf\/818B98CE8FD144A18F6EEEC567B7EE92","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:50:49Z","timestamp":1781769049000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.sciengine.com\/doi\/10.3724\/2096-7004.di.2025.0044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":10,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,6,8]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.3724\/2096-7004.di.2025.0044","relation":{},"ISSN":["2096-7004"],"issn-type":[{"value":"2096-7004","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6,1]]}}}