{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:06:40Z","timestamp":1791911200594,"version":"4.3.4"},"reference-count":101,"publisher":"Association for Computing Machinery (ACM)","issue":"5","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Softw. Eng. Methodol."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>Ethical and social risks persist as a crucial yet challenging topic in human-AI interactions, especially in ensuring the safe usage of natural language processing (NLP). The emergence of large language models (LLMs) like ChatGPT introduces the potential for exacerbating this concern. However, prior works on the ethics and risks of emergent LLMs either overlook the practical implications in real-world scenarios, lag behind rapid NLP advancements, lack user consensus on ethical risks, or fail to holistically address the entire spectrum of ethical considerations. In this article, we comprehensively evaluate, qualitatively explore, and catalog ethical dilemmas and risks in ChatGPT through benchmarking with eight representative datasets and red teaming involving diverse case studies. Our findings show that while ChatGPT demonstrates superior safety performance on benchmark datasets, its guardrails can be bypassed via our manually curated examples, revealing not only the limitations of current benchmarks for risk assessment but also unexplored risks in five distinct scenarios, including social bias in code generation, bias in cross-lingual question answering, toxic language in personalized dialogue, misleading information from hallucination, and prompt injections for unethical behaviors. We conclude with implications from red teaming ChatGPT and recommendations for designing future responsible large language models.<\/jats:p>","DOI":"10.1145\/3747288","type":"journal-article","created":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T09:12:37Z","timestamp":1751620357000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Bypassing Guardrails: Lessons Learned from Red Teaming ChatGPT"],"prefix":"10.1145","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5760-5188","authenticated-orcid":false,"given":"Terry Yue","family":"Zhuo","sequence":"first","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2281-2504","authenticated-orcid":false,"given":"Yujin","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Melbourne, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2011-9618","authenticated-orcid":false,"given":"Chunyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Technical University of Munich, Heilbronn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3728-9541","authenticated-orcid":false,"given":"Xiaoning","family":"Du","sequence":"additional","affiliation":[{"name":"Monash University, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7663-1421","authenticated-orcid":false,"given":"Zhenchang","family":"Xing","sequence":"additional","affiliation":[{"name":"CSIRO, Canberra, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Junyan Chen Jason (Zengzhong) Li and Rangan Majumder. 2021. Make every feature binary: A 135B parameter sparse neural network for massively improved search relevance. Retrieved from https:\/\/www.microsoft.com\/en-us\/research\/blog\/make-every-feature-binary-a-135b-parameter-sparse-neural-network-for-massively-improved-search-relevance\/"},{"key":"e_1_3_2_3_2","unstructured":"Pandu Nayak. 2021. MUM: A New AI Milestone for Understanding Information. Retrieved from https:\/\/blog.google\/products\/search\/introducing-mum\/"},{"key":"e_1_3_2_4_2","unstructured":"Jaybird. 2022. ChatGPT Has a Handful of Ethical Constraints that Are Currently Being Tested. Retrieved from https:\/\/ordinary-times.com\/2022\/12\/02\/chatgpt-has-a-handful-of-ethical-constraints-that-are-currently-being-tested\/"},{"key":"e_1_3_2_5_2","volume-title":"SOUPS@ USENIX Security Symposium","author":"Abdi Noura","year":"2019","unstructured":"Noura Abdi, Kopo M. Ramokapane, and Jose M. Such. 2019. More than smart speakers: Security and privacy perceptions of smart home personal assistants. In SOUPS@ USENIX Security Symposium."},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"e_1_3_2_7_2","unstructured":"Armen Aghajanyan Lili Yu Alexis Conneau Wei-Ning Hsu Karen Hambardzumyan Susan Zhang Stephen Roller Naman Goyal Omer Levy and Luke Zettlemoyer. 2023. Scaling laws for generative mixed-modal language models. arXiv:2301.03728. Retrieved from https:\/\/arxiv.org\/abs\/2301.03728"},{"key":"e_1_3_2_8_2","unstructured":"Loubna Ben Allal Raymond Li Denis Kocetkov Chenghao Mou Christopher Akiki Carlos Munoz Ferrandis Niklas Muennighoff Mayank Mishra Alex Gu Manan Dey et al. 2023. SantaCoder: Don\u2019t reach for the stars!. arXiv:2301.03988. Retrieved from https:\/\/arxiv.org\/abs\/2301.03988"},{"key":"e_1_3_2_9_2","unstructured":"Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell Jackson Kernion Andy Jones Anna Chen Anna Goldie Azalia Mirhoseini Cameron McKinnon et al. 2022. Constitutional AI: Harmlessness from AI feedback. arXiv:2212.08073. Retrieved from https:\/\/arxiv.org\/abs\/2212.08073"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"e_1_3_2_12_2","unstructured":"Rishi Bommasani Drew A. Hudson Ehsan Adeli Russ Altman Simran Arora Sydney von Arx Michael S. Bernstein Jeannette Bohg Antoine Bosselut Emma Brunskill et al. 2021. On the opportunities and risks of foundation models. arXiv:2108.07258. Retrieved from https:\/\/arxiv.org\/abs\/2108.07258"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Zal\u00e1n Borsos Rapha\u00ebl Marinier Damien Vincent Eugene Kharitonov Olivier Pietquin Matt Sharifi Olivier Teboul David Grangier Marco Tagliasacchi and Neil Zeghidour. 2022. Audiolm: A language modeling approach to audio generation. arXiv:2209.03143. Retrieved from https:\/\/arxiv.org\/abs\/2209.03143","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"e_1_3_2_14_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. 2020. Language models are few-shot learners. In Advances in Neural Information Processing Systems, Vol. 33, 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_15_2","unstructured":"Tom B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. arXiv:2005.14165. Retrieved from https:\/\/arxiv.org\/abs\/2005.14165"},{"key":"e_1_3_2_16_2","article-title":"Editing factual knowledge in language models","author":"De Cao Nicola","year":"2021","unstructured":"Nicola De Cao, Wilker Aziz, and Ivan Titov. 2021. Editing factual knowledge in language models. In Proceedings of the Conference on Empirical Methods in Natural Language Processing.","journal-title":"In"},{"key":"e_1_3_2_17_2","volume-title":"USENIX Security Symposium","volume":"6","author":"Carlini Nicholas","year":"2021","unstructured":"Nicholas Carlini, Florian Tramer, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom B. Brown, Dawn Song, Ulfar Erlingsson, et al. 2021. Extracting training data from large language models. In USENIX Security Symposium, Vol. 6."},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Douglas Eck Jeff Dean Slav Petrov Noah Fiedel Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts et al. 2022. PaLM: Scaling language modeling with pathways. arXiv:2204.02311. DOI: 10.48550\/ARXIV.2204.02311","DOI":"10.48550\/ARXIV.2204.02311"},{"key":"e_1_3_2_19_2","unstructured":"Arijit Ghosh Chowdhury Md Mofijul Islam Vaibhav Kumar Faysal Hossain Shezan Vinija Jain and Aman Chadha. 2024. Breaking down the defenses: A comparative survey of attacks on large language models. arXiv:2403.04786. Retrieved from https:\/\/arxiv.org\/abs\/2403.04786"},{"key":"e_1_3_2_20_2","first-page":"2924","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Clark Christopher","year":"2019","unstructured":"Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. 2019. BoolQ: Exploring the surprising difficulty of natural yes\/no questions. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1, Long and Short Papers, 2924\u20132936."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"e_1_3_2_22_2","unstructured":"Marta R. Costa-Juss\u00e0 James Cross Onur \u00c7elebi Maha Elbayad Kenneth Heafield Kevin Heffernan Elahe Kalbassi Janice Lam Daniel Licht Jean Maillard et al. 2022. No language left behind: Scaling human-centered machine translation. arXiv:2207.04672. Retrieved from https:\/\/arxiv.org\/abs\/2207.04672"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445924"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.375"},{"key":"e_1_3_2_25_2","first-page":"421","volume-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society","volume":"7","author":"Feffer Michael","year":"2024","unstructured":"Michael Feffer, Anusha Sinha, Wesley H. Deng, Zachary C. Lipton, and Hoda Heidari. 2024. Red-teaming for generative AI: Silver bullet or security theater? In Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society, Vol. 7, 421\u2013437."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3232676"},{"key":"e_1_3_2_27_2","unstructured":"Deep Ganguli Liane Lovitt Jackson Kernion Amanda Askell Yuntao Bai Saurav Kadavath Ben Mann Ethan Perez Nicholas Schiefer Kamal Ndousse et al. 2022. Red teaming language models to reduce harms: Methods scaling behaviors and lessons learned. arXiv:2209.07858. Retrieved from https:\/\/arxiv.org\/abs\/2209.07858"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.117"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"e_1_3_2_30_2","volume-title":"ICLR 2024 Workshop on Secure and Trustworthy Large Language Models","author":"Geiping Jonas","year":"2024","unstructured":"Jonas Geiping, Alex Stein, Manli Shu, Khalid Saifullah, Yuxin Wen, and Tom Goldstein. 2024. Coercing LLMs to do and reveal (almost) anything. In ICLR 2024 Workshop on Secure and Trustworthy Large Language Models."},{"key":"e_1_3_2_31_2","unstructured":"Aaron Gokaslan and Vanya Cohen. 2019. OpenWebText Corpus. Retrieved from http:\/\/Skylion007.github.io\/OpenWebTextCorpus"},{"key":"e_1_3_2_32_2","unstructured":"Yoav Goldberg. 2023. Some remarks on Large Language Model. Retrieved from https:\/\/gist.github.com\/yoavg\/59d174608e92e845c8994ac2e234c8a9"},{"key":"e_1_3_2_33_2","unstructured":"Josh A. Goldstein Girish Sastry Micah Musser Renee DiResta Matthew Gentzel and Katerina Sedova. 2023. Generative language models and automated influence operations: Emerging threats and potential mitigations. arXiv:2301.04246. Retrieved from https:\/\/arxiv.org\/abs\/2301.04246"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1177\/2053951719897945"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00474"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21321"},{"key":"e_1_3_2_37_2","article-title":"CATER: Intellectual property protection on text generation APIs via conditional watermarks","author":"He Xuanli","year":"2022","unstructured":"Xuanli He, Qiongkai Xu, Yi Zeng, Lingjuan Lyu, Fangzhao Wu, Jiwei Li, and Ruoxi Jia. 2022. CATER: Intellectual property protection on text generation APIs via conditional watermarks. In Advances in Neural Information Processing Systems.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278777"},{"key":"e_1_3_2_39_2","volume-title":"Proceedings of the 12th International Conference on Learning Representations","author":"Hong Zhang-Wei","year":"2024","unstructured":"Zhang-Wei Hong, Idan Shenfeld, Tsun-Hsuan Wang, Yung-Sung Chuang, Aldo Pareja, James R. Glass, Akash Srivastava, and Pulkit Agrawal. 2024. Curiosity-driven red-teaming for large language models. In Proceedings of the 12th International Conference on Learning Representations."},{"key":"e_1_3_2_40_2","article-title":"THEMIS: Towards practical intellectual property protection for post-deployment on-device deep learning models","author":"Huang Yujin","year":"2025","unstructured":"Yujin Huang, Zhi Zhang, Qingchuan Zhao, Xingliang Yuan, and Chunyang Chen. 2025. THEMIS: Towards practical intellectual property protection for post-deployment on-device deep learning models. In 34th USENIX Security Symposium (USENIX Security 25).","journal-title":"34th USENIX Security Symposium (USENIX Security 25)"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583348"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0088-2"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.560"},{"key":"e_1_3_2_44_2","first-page":"10697","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Kandpal Nikhil","year":"2022","unstructured":"Nikhil Kandpal, Eric Wallace, and Colin Raffel. 2022. Deduplicating training data mitigates privacy risks in language models. In Proceedings of the International Conference on Machine Learning. PMLR, 10697\u201310707."},{"key":"e_1_3_2_45_2","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling laws for neural language models. arXiv:2001.08361. Retrieved from https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_2_46_2","unstructured":"Zachary Kenton Tom Everitt Laura Weidinger Iason Gabriel Vladimir Mikulik and Geoffrey Irving. 2021. Alignment of language agents. arXiv:2103.14659. Retrieved from https:\/\/arxiv.org\/abs\/2103.14659"},{"key":"e_1_3_2_47_2","unstructured":"John Kirchenbauer Jonas Geiping Yuxin Wen Jonathan Katz Ian Miers and Tom Goldstein. 2023. A watermark for large language models. arXiv:2301.10226. Retrieved from https:\/\/arxiv.org\/abs\/2301.10226"},{"key":"e_1_3_2_48_2","first-page":"2611","article-title":"Bias out-of-the-box: An empirical analysis of intersectional occupational biases in popular generative language models","volume":"34","author":"Kirk Hannah Rose","year":"2021","unstructured":"Hannah Rose Kirk, Yennie Jun, Filippo Volpin, Haider Iqbal, Elias Benussi, Frederic Dreyer, Aleksandar Shtedritski, and Yuki Asano. 2021. Bias out-of-the-box: An empirical analysis of intersectional occupational biases in popular generative language models. In Advances in Neural Information Processing Systems, Vol. 34, 2611\u20132624.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_49_2","unstructured":"Felix Kreuk Gabriel Synnaeve Adam Polyak Uriel Singer Alexandre D\u00e9fossez Jade Copet Devi Parikh Yaniv Taigman and Yossi Adi. 2022. Audiogen: Textually guided audio generation. arXiv:2209.15352. Retrieved from https:\/\/arxiv.org\/abs\/2209.15352"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjmed.2020.07.012"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.577"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502030"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1259"},{"key":"e_1_3_2_54_2","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar et al. 2022. Holistic evaluation of language models. arXiv:2211.09110. Retrieved from https:\/\/arxiv.org\/abs\/2211.09110"},{"key":"e_1_3_2_55_2","first-page":"6565","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Wu Chiyu","year":"2021","unstructured":"Chiyu Wu, Paul Pu Liang, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2021. Towards understanding and mitigating social biases in language models. In Proceedings of the International Conference on Machine Learning. PMLR, 6565\u20136576."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.17654"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"e_1_3_2_58_2","first-page":"386","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Liu Xin","year":"2024","unstructured":"Xin Liu, Yichen Zhu, Jindong Gu, Yunshi Lan, Chao Yang, and Yu Qiao. 2024. Mm-safetybench: A benchmark for safety evaluation of multimodal large language models. In Proceedings of the European Conference on Computer Vision. Springer, 386\u2013403."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nuse-1.5"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002491"},{"key":"e_1_3_2_61_2","unstructured":"Kris McGuffie and Alex Newhouse. 2020. The radicalization risks of GPT-3 and advanced neural language models. arXiv:2009.06807. Retrieved from https:\/\/arxiv.org\/abs\/2009.06807"},{"key":"e_1_3_2_62_2","unstructured":"Timothy R. McIntosh Teo Susnjak Nalin Arachchilage Tong Liu Paul Watters and Malka N. Halgamuge. 2024. Inadequacies of large language model benchmarks in the era of generative artificial intelligence. arXiv:2402.09880. Retrieved from https:\/\/arxiv.org\/abs\/2402.09880"},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1260"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-2014"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sustainlp-1.23"},{"key":"e_1_3_2_66_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Mitchell Eric","year":"2022","unstructured":"Eric Mitchell, Charles Lin, Antoine Bosselut, Chelsea Finn, and Christopher D. Manning. 2022. Fast model editing at scale. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.416"},{"key":"e_1_3_2_68_2","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, et al. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, Vol. 35, 27730\u201327744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"key":"e_1_3_2_70_2","doi-asserted-by":"crossref","unstructured":"Ethan Perez Saffron Huang Francis Song Trevor Cai Roman Ring John Aslanides Amelia Glaese Nat McAleese and Geoffrey Irving. 2022. Red teaming language models with language models. arXiv:2202.03286. Retrieved from https:\/\/arxiv.org\/abs\/2202.03286","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","unstructured":"Nathaniel Persily and Joshua A. Tucker. 2020. Social media and democracy: The state of the field prospects for reform. DOI: 10.1017\/9781108890960","DOI":"10.1017\/9781108890960"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-3049"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6319"},{"key":"e_1_3_2_74_2","unstructured":"Jack W. Rae Sebastian Borgeaud Trevor Cai Katie Millican Jordan Hoffmann Francis Song John Aslanides Sarah Henderson Roman Ring Susannah Young et al. 2021. Scaling language models: Methods analysis & insights from training gopher. arXiv:2112.11446. Retrieved from https:\/\/arxiv.org\/abs\/2112.11446"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3362031"},{"key":"e_1_3_2_76_2","unstructured":"Teven Le Scao Angela Fan Christopher Akiki Ellie Pavlick Suzana Ili\u0107 Daniel Hesslow Roman Castagn\u00e9 Alexandra Sasha Luccioni Fran\u00e7ois Yvon Matthias Gall\u00e9 et al. 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv:2211.05100. Retrieved from https:\/\/arxiv.org\/abs\/2211.05100"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00380"},{"key":"e_1_3_2_78_2","unstructured":"Elizabeth Seger Shahar Avin Gavin Pearson Mark Briers Se\u00e1n \u00d3. Heigeartaigh Helena Bacon Henry Ajder Claire Alderson Fergus Anderson Joseph Baddeley et al. 2020. Tackling threats to informed decision-making in democratic societies: Promoting epistemic security in a technologically-advanced world. Retrieved from https:\/\/www.turing.ac.uk\/sites\/default\/files\/2020-10\/epistemic-security-report_final.pdf"},{"key":"e_1_3_2_79_2","first-page":"2659","volume-title":"Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security","author":"Man Si Wai","year":"2022","unstructured":"Wai Man Si, Michael Backes, Jeremy Blackburn, Emiliano De Cristofaro, Gianluca Stringhini, Savvas Zannettou, and Yang Zhang. 2022. Why so toxic? Measuring and triggering toxic behavior in Open-Domain chatbots. In Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, 2659\u20132673."},{"key":"e_1_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat5991"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.bigscience-1.3"},{"key":"e_1_3_2_82_2","unstructured":"Marta Ruiz Costa-Juss\u00e0 James Cross Onur Celebi Maha Elbayad Kenneth Heafield Kevin Heffernan Elahe Kalbassi Janice Lam Daniel Licht Jean Maillard et al. 2022. No language left behind: Scaling human-centered machine translation. arXiv:2207.04672. Retrieved from https:\/\/arxiv.org\/abs\/2207.04672"},{"key":"e_1_3_2_83_2","unstructured":"Neil C. Thompson Kristjan Greenewald Keeheon Lee and Gabriel F. Manso. 2020. The computational limits of deep learning. arXiv:2007.05558. Retrieved from https:\/\/arxiv.org\/abs\/2007.05558"},{"key":"e_1_3_2_84_2","unstructured":"Marcos Treviso Tianchu Ji Ji-Ung Lee Betty van Aken Qingqing Cao Manuel R. Ciosici Michael Hassid Kenneth Heafield Sara Hooker Pedro H. Martins et al. 2022. Efficient methods for natural language processing: A survey. arXiv:2209.00099. Retrieved from https:\/\/arxiv.org\/abs\/2209.00099"},{"key":"e_1_3_2_85_2","unstructured":"Apurv Verma Satyapriya Krishna Sebastian Gehrmann Madhavan Seshadri Anu Pradhan Tom Ault Leslie Barrett David Rabinowitz John A. Doucette and NhatHai Phan. 2024. Operationalizing a threat model for red-teaming large language models (LLMs). arXiv:2407.14937. Retrieved from https:\/\/arxiv.org\/abs\/2407.14937"},{"key":"e_1_3_2_86_2","unstructured":"Pablo Villalobos Jaime Sevilla Lennart Heim Tamay Besiroglu Marius Hobbhahn and Anson Ho. 2022. Will we run out of data? An analysis of the limits of scaling datasets in machine learning. arXiv:2211.04325. Retrieved from https:\/\/arxiv.org\/abs\/2211.04325"},{"key":"e_1_3_2_87_2","first-page":"2835","article-title":"Emergent abilities of large language models","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, et al. 2022. Emergent abilities of large language models. Transactions on Machine Learning Research 2022 (2022), 2835\u20138856.","journal-title":"Transactions on Machine Learning Research"},{"key":"e_1_3_2_88_2","unstructured":"Mengyi Wei and Zhixuan Zhou. 2022. Ai ethics issues in real world: Evidence from ai incident database. arXiv:2206.07635. Retrieved from https:\/\/arxiv.org\/abs\/2206.07635"},{"key":"e_1_3_2_89_2","unstructured":"Laura Weidinger John Mellor Maribeth Rauh Conor Griffin Jonathan Uesato Po-Sen Huang Myra Cheng Mia Glaese Borja Balle Atoosa Kasirzadeh et al. 2021. Ethical and social risks of harm from language models. arXiv:2112.04359. Retrieved from https:\/\/arxiv.org\/abs\/2112.04359"},{"key":"e_1_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.210"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3144592.3144598"},{"key":"e_1_3_2_92_2","first-page":"795","article-title":"Sustainable AI: Environmental implications, challenges and opportunities","volume":"4","author":"Wu Carole-Jean","year":"2022","unstructured":"Carole-Jean Wu, Ramya Raghavendra, Udit Gupta, Bilge Acun, Newsha Ardalani, Kiwan Maeng, Gloria Chang, Fiona Aga, Jinshi Huang, Charles Bai, et al. 2022. Sustainable AI: Environmental implications, challenges and opportunities. Proceedings of Machine Learning and Systems 4 (2022), 795\u2013813.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_93_2","unstructured":"Jing Xu Da Ju Margaret Li Y.-Lan Boureau Jason Weston and Emily Dinan. 2020. Recipes for safety in open-domain chatbots. arXiv:2010.07079. Retrieved from https:\/\/arxiv.org\/abs\/2010.07079"},{"key":"e_1_3_2_94_2","unstructured":"Dongchao Yang Jianwei Yu Helin Wang Wen Wang Chao Weng Yuexian Zou and Dong Yu. 2022. Diffsound: Discrete diffusion model for text-to-sound generation. arXiv:2207.09983. Retrieved from https:\/\/arxiv.org\/abs\/2207.09983"},{"key":"e_1_3_2_95_2","doi-asserted-by":"crossref","unstructured":"Yifan Yao Jinhao Duan Kaidi Xu Yuanfang Cai Zhibo Sun and Yue Zhang. 2024. A survey on large language model (LLM) security and privacy: The good the bad and the ugly. High-Confidence Computing 4 2 (2024) 100211.","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3479594"},{"key":"e_1_3_2_97_2","doi-asserted-by":"crossref","unstructured":"Chaoning Zhang Philipp Benz Chenguo Lin Adil Karjauv Jing Wu and In So Kweon. 2021. A survey on universal adversarial attack. arXiv:2103.01498. Retrieved from https:\/\/arxiv.org\/abs\/2103.01498","DOI":"10.24963\/ijcai.2021\/635"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"e_1_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1205"},{"key":"e_1_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_102_2","unstructured":"Chen Zhu Ankit Singh Rawat Manzil Zaheer Srinadh Bhojanapalli Daliang Li Felix X. Yu and Sanjiv Kumar. 2020. Modifying memories in transformer models. arXiv:2012.00363. Retrieved from https:\/\/arxiv.org\/abs\/2207.09983"}],"container-title":["ACM Transactions on Software Engineering and Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3747288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T06:34:46Z","timestamp":1777098886000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3747288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":101,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3747288"],"URL":"https:\/\/doi.org\/10.1145\/3747288","relation":{},"ISSN":["1049-331X","1557-7392"],"issn-type":[{"value":"1049-331X","type":"print"},{"value":"1557-7392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"assertion":[{"value":"2024-09-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}