{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:30:56Z","timestamp":1772695856234,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T00:00:00Z","timestamp":1794268800000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100006227","name":"Lawrence Livermore National Laboratory","doi-asserted-by":"publisher","award":["DE-AC52-07NA27344"],"award-info":[{"award-number":["DE-AC52-07NA27344"]}],"id":[{"id":"10.13039\/100006227","id-type":"DOI","asserted-by":"publisher"}]},{"name":"LDRD Program Project","award":["No. 24-ERD-058"],"award-info":[{"award-number":["No. 24-ERD-058"]}]},{"name":"ND-IBM Tech Ethics Lab"},{"name":"NSF-Simons SkAI Institute"},{"name":"National Institutes of Health (NIH)","award":["#R01AG091762"],"award-info":[{"award-number":["#R01AG091762"]}]},{"name":"Google Research Scholar Award"},{"name":"Cisco gift grant"},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["#2312862, #2440542"],"award-info":[{"award-number":["#2312862, #2440542"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761448","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T01:03:27Z","timestamp":1762563807000},"page":"6825-6828","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Socially Responsible and Trustworthy Generative Foundation Models: Principles, Challenges, and Practices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8315-7972","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"first","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0937-1046","authenticated-orcid":false,"given":"Canyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Northwestern University, Chicago, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2503-2522","authenticated-orcid":false,"given":"Lu","family":"Cheng","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0043-4593","authenticated-orcid":false,"given":"Bhavya","family":"Kailkhura","sequence":"additional","affiliation":[{"name":"Lawrence Livermore National Laboratory, Livermore, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3932-5956","authenticated-orcid":false,"given":"Nitesh","family":"Chawla","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3574-5665","authenticated-orcid":false,"given":"Xiangliang","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Notre Dame, South Bend, IN, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2942287"},{"key":"e_1_3_2_1_2_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems 30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_3_1","article-title":"Regulation (EU) 2024\/1689 of the European Parliament and of the Council of 13 June 2024 laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). https:\/\/eur-lex.europa.eu\/eli\/reg\/2024\/1689\/oj\/eng","author":"Union European","year":"2024","unstructured":"European Union. 2024. Regulation (EU) 2024\/1689 of the European Parliament and of the Council of 13 June 2024 laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). https:\/\/eur-lex.europa.eu\/eli\/reg\/2024\/1689\/oj\/eng. Official Journal of the European Union, L 2024\/1689, 12 July 2024.","journal-title":"Official Journal of the European Union"},{"key":"e_1_3_2_1_4_1","volume-title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2020","author":"Gehman Samuel","year":"2020","unstructured":"Samuel Gehman, Suchin Gururangan, Maarten Sap, et al. 2020. RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models. In Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, 3356--3369. https:\/\/aclanthology.org\/2020.findingsemnlp.301\/"},{"key":"e_1_3_2_1_5_1","unstructured":"Yue Huang Chujie Gao Siyuan Wu Haoran Wang Xiangqi Wang Yujun Zhou YanboWang Jiayi Ye Jiawen Shi Qihui Zhang et al. 2025. On the trustworthiness of generative foundation models: Guideline assessment and perspective. arXiv preprint arXiv:2502.14296 (2025)."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Huang Yue","year":"2024","unstructured":"Yue Huang, Lichao Sun, Haoran Wang, et al. 2024. TrustLLM: Trustworthiness in Large Language Models. In Proceedings of the 41st International Conference on Machine Learning, Vol. 235. PMLR, 35225--35240. https:\/\/proceedings.mlr.press\/v235\/huang24x.html"},{"key":"e_1_3_2_1_7_1","unstructured":"Hakan Inan Kartikeya Upasani Jianfeng Chi Rashi Rungta Krithika Iyer Yuning Mao Michael Tontchev Qing Hu Brian Fuller Davide Testuggine et al. 2023. Llama guard: Llm-based input-output safeguard for human-ai conversations. arXiv preprint arXiv:2312.06674 (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Mazeika Mantas","year":"2024","unstructured":"Mantas Mazeika, Long Phan, Xuwang Yin, et al. 2024. HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal. In Proceedings of the 41st International Conference on Machine Learning, Vol. 235. PMLR, 35181--35224. https:\/\/proceedings.mlr.press\/v235\/mazeika24a.html"},{"key":"e_1_3_2_1_10_1","unstructured":"National Institute of Standards and Technology (NIST). 2023. Artificial Intelligence Risk Management Framework (AI RMF 1.0). Technical Report NIST AI 100--1. U.S. Department of Commerce. https:\/\/nvlpubs.nist.gov\/nistpubs\/ai\/nist.ai.100--1.pdf"},{"key":"e_1_3_2_1_11_1","unstructured":"OpenAI. 2025. Moderation Guide. https:\/\/platform.openai.com\/docs\/guides\/moderation."},{"key":"e_1_3_2_1_12_1","volume-title":"BBQ: A Hand-Built Bias Benchmark for Question Answering. In Findings of the Association for Computational Linguistics: ACL 2022","author":"Parrish Alicia","year":"2022","unstructured":"Alicia Parrish, Rachel Rudinger, Tal Linzen, et al. 2022. BBQ: A Hand-Built Bias Benchmark for Question Answering. In Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics, 2601-- 2611. https:\/\/aclanthology.org\/2022.findings-acl.165\/"},{"key":"e_1_3_2_1_13_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert and Others. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288 [cs.CL]"},{"key":"e_1_3_2_1_14_1","unstructured":"Boxin Wang Weixin Chen Hengzhi Pei Chulin Xie Mintong Kang Chenhui Zhang Chejian Xu Zidi Xiong Ritik Dutta Rylan Schaeffer et al. 2023. DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models. arXiv preprint arXiv:2306.11698 (2023)."},{"key":"e_1_3_2_1_15_1","volume-title":"TRUSTEVAL: A Dynamic Evaluation Toolkit on Trustworthiness of Generative Foundation Models. In Proceedings of the 2025 Conference of the Nations of the Americas","author":"Wang Yanbo","year":"2025","unstructured":"Yanbo Wang, Jiayi Ye, Siyuan Wu, Chujie Gao, Yue Huang, Xiuying Chen, Yue Zhao, and Xiangliang Zhang. 2025. TRUSTEVAL: A Dynamic Evaluation Toolkit on Trustworthiness of Generative Foundation Models. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations). Association for Computational Linguistics, Albuquerque, New Mexico, 70--84. https:\/\/aclanthology.org\/2025.naacl-demo.8\/"},{"key":"e_1_3_2_1_16_1","volume-title":"On prompt-driven safeguarding for large language models. arXiv preprint arXiv:2401.18018","author":"Zheng Chujie","year":"2024","unstructured":"Chujie Zheng, Fan Yin, Hao Zhou, Fandong Meng, Jie Zhou, Kai-Wei Chang, Minlie Huang, and Nanyun Peng. 2024. On prompt-driven safeguarding for large language models. arXiv preprint arXiv:2401.18018 (2024)."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3746252.3761448","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761448","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:47:03Z","timestamp":1765507623000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761448"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":16,"alternative-id":["10.1145\/3746252.3761448","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761448","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}