{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T19:12:24Z","timestamp":1765825944641,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,8]],"date-time":"2023-08-08T00:00:00Z","timestamp":1691452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,8]]},"DOI":"10.1145\/3600211.3604748","type":"proceedings-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T18:41:37Z","timestamp":1693334497000},"page":"950-951","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Safety Issues in Conversational Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0664-1458","authenticated-orcid":false,"given":"Jinhwa","family":"Kim","sequence":"first","affiliation":[{"name":"Computer Science, University of California, Irvine, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,8,29]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_2_1_1_1","DOI":"10.1145\/3561390"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_2_1","DOI":"10.1109\/WIFS47025.2019.9035090"},{"doi-asserted-by":"crossref","unstructured":"Ameet Deshpande Vishvak Murahari Tanmay Rajpurohit Ashwin Kalyan and Karthik Narasimhan. 2023. Toxicity in ChatGPT: Analyzing Persona-assigned Language Models. arxiv:2304.05335\u00a0[cs.CL]","key":"e_1_3_2_1_3_1","DOI":"10.18653\/v1\/2023.findings-emnlp.88"},{"key":"e_1_3_2_1_4_1","volume-title":"Realtoxicityprompts: Evaluating neural toxic degeneration in language models. arXiv preprint arXiv:2009.11462","author":"Gehman Samuel","year":"2020","unstructured":"Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah\u00a0A Smith. 2020. Realtoxicityprompts: Evaluating neural toxic degeneration in language models. arXiv preprint arXiv:2009.11462 (2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"Toward deconfounding the influence of entity demographics for question answering accuracy. arXiv preprint arXiv:2104.07571","author":"Gor Maharshi","year":"2021","unstructured":"Maharshi Gor, Kellie Webster, and Jordan Boyd-Graber. 2021. Toward deconfounding the influence of entity demographics for question answering accuracy. arXiv preprint arXiv:2104.07571 (2021)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.33640\/2405-609X.3157"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings for the First International Workshop on Social Threats in Online Conversations: Understanding and Management.","author":"Kim Jinhwa","year":"2020","unstructured":"Jinhwa Kim, Yoon\u00a0Jo Kim, Mitra Behzadi, and Ian\u00a0G Harris. 2020. Analysis of online conversations to detect cyberpredators using recurrent neural networks. In Proceedings for the First International Workshop on Social Threats in Online Conversations: Understanding and Management."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_8_1","DOI":"10.1016\/j.jadohealth.2018.03.012"},{"key":"e_1_3_2_1_9_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems 35 (2022), 27730\u201327744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","volume-title":"Toxicity detection: Does context really matter?arXiv preprint arXiv:2006.00998","author":"Pavlopoulos John","year":"2020","unstructured":"John Pavlopoulos, Jeffrey Sorensen, Lucas Dixon, Nithum Thain, and Ion Androutsopoulos. 2020. Toxicity detection: Does context really matter?arXiv preprint arXiv:2006.00998 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"Characteristics of harmful text: Towards rigorous benchmarking of language models. arXiv preprint arXiv:2206.08325","author":"Rauh Maribeth","year":"2022","unstructured":"Maribeth Rauh, John Mellor, Jonathan Uesato, Po-Sen Huang, Johannes Welbl, Laura Weidinger, Sumanth Dathathri, Amelia Glaese, Geoffrey Irving, Iason Gabriel, 2022. Characteristics of harmful text: Towards rigorous benchmarking of language models. arXiv preprint arXiv:2206.08325 (2022)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1145\/3469859"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.18653\/v1\/N18-2002"},{"unstructured":"Kurt Shuster Jing Xu Mojtaba Komeili Da Ju Eric\u00a0Michael Smith Stephen Roller Megan Ung Moya Chen Kushal Arora Joshua Lane Morteza Behrooz William Ngan Spencer Poff Naman Goyal Arthur Szlam Y-Lan Boureau Melanie Kambadur and Jason Weston. 2022. BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage. arxiv:2208.03188\u00a0[cs.CL]","key":"e_1_3_2_1_14_1"},{"key":"e_1_3_2_1_15_1","volume-title":"Challenges in detoxifying language models. arXiv preprint arXiv:2109.07445","author":"Welbl Johannes","year":"2021","unstructured":"Johannes Welbl, Amelia Glaese, Jonathan Uesato, Sumanth Dathathri, John Mellor, Lisa\u00a0Anne Hendricks, Kirsty Anderson, Pushmeet Kohli, Ben Coppin, and Po-Sen Huang. 2021. Challenges in detoxifying language models. arXiv preprint arXiv:2109.07445 (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Toxicity Detection can be Sensitive to the Conversational Context. ArXiv abs\/2111.10223","author":"Xenos Alexandros","year":"2021","unstructured":"Alexandros Xenos, John Pavlopoulos, Ion Androutsopoulos, Lucas Dixon, Jeffrey Sorensen, and Leo Laugier. 2021. Toxicity Detection can be Sensitive to the Conversational Context. ArXiv abs\/2111.10223 (2021)."},{"unstructured":"Terry\u00a0Yue Zhuo Yujin Huang Chunyang Chen and Zhenchang Xing. 2023. Exploring AI Ethics of ChatGPT: A Diagnostic Analysis. arxiv:2301.12867\u00a0[cs.CL]","key":"e_1_3_2_1_17_1"}],"event":{"sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"],"acronym":"AIES '23","name":"AIES '23: AAAI\/ACM Conference on AI, Ethics, and Society","location":"Montr\u00e9al QC Canada"},"container-title":["Proceedings of the 2023 AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600211.3604748","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3600211.3604748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T18:55:31Z","timestamp":1750272931000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3600211.3604748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,8]]},"references-count":17,"alternative-id":["10.1145\/3600211.3604748","10.1145\/3600211"],"URL":"https:\/\/doi.org\/10.1145\/3600211.3604748","relation":{},"subject":[],"published":{"date-parts":[[2023,8,8]]},"assertion":[{"value":"2023-08-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}