{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T10:52:00Z","timestamp":1781693520724,"version":"3.54.5"},"reference-count":28,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3393245","type":"journal-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T17:31:29Z","timestamp":1713979889000},"page":"64717-64726","source":"Crossref","is-referenced-by-count":4,"title":["Beyond Binary Classification: A Fine-Grained Safety Dataset for Large Language Models"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0801-9692","authenticated-orcid":false,"given":"Jia","family":"Yu","sequence":"first","affiliation":[{"name":"School of Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Li","sequence":"additional","affiliation":[{"name":"School of Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenzhong","family":"Lan","sequence":"additional","affiliation":[{"name":"School of Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref2","volume-title":"An important next step on our AI journey","author":"Pichai","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00742-2"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref5","first-page":"492","article-title":"LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Int. Conf. Robot Learn.","author":"Shah"},{"key":"ref6","article-title":"ChatGPT for robotics: Design principles and model abilities","author":"Vemprala","year":"2023","journal-title":"arXiv:2306.17582"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.88"},{"key":"ref8","article-title":"Ethical and social risks of harm from language models","author":"Weidinger","year":"2021","journal-title":"arXiv:2112.04359"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"ref10","article-title":"BeaverTails: Towards improved safety alignment of LLM via a human-preference dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ji"},{"key":"ref11","article-title":"Safe RLHF: Safe reinforcement learning from human feedback","author":"Dai","year":"2023","journal-title":"arXiv:2310.12773"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"key":"ref13","article-title":"Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned","author":"Ganguli","year":"2022","journal-title":"arXiv:2209.07858"},{"key":"ref14","article-title":"TruthfulQA: Measuring how models mimic human falsehoods","author":"Lin","year":"2021","journal-title":"arXiv:2109.07958"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"key":"ref16","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref17","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","author":"He","year":"2020","journal-title":"arXiv:2006.03654"},{"issue":"240","key":"ref18","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.870"},{"key":"ref20","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zheng"},{"key":"ref21","article-title":"AlpacaFarm: A simulation framework for methods that learn from human feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Dubois"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref23","article-title":"PandaLM: An automatic evaluation benchmark for LLM instruction tuning optimization","author":"Wang","year":"2023","journal-title":"arXiv:2306.05087"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-6001"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3560260"},{"key":"ref26","article-title":"Evaluating quality of chatbots and intelligent conversational agents","author":"Radziwill","year":"2017","journal-title":"arXiv:1704.04579"},{"key":"ref27","article-title":"A framework for evaluation of machine reading comprehension gold standards","author":"Schlegel","year":"2020","journal-title":"arXiv:2003.04642"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10507773.pdf?arnumber=10507773","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T17:27:17Z","timestamp":1715362037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10507773\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3393245","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}