{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T03:49:01Z","timestamp":1783136941150,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":182,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791726","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:36Z","timestamp":1776053556000},"page":"1-37","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Who Controls the Conversation? User Perspectives on Generative AI (LLM) System Prompts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-9672-8087","authenticated-orcid":false,"given":"Anna","family":"Neumann","sequence":"first","affiliation":[{"name":"Research Centre Trust, UA Ruhr, University Duisburg-Essen, Duisburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8961-2270","authenticated-orcid":false,"given":"Yulu","family":"Pi","sequence":"additional","affiliation":[{"name":"Research Centre Trust, UA Ruhr, University Duisburg-Essen, Duisburg, Germany and University of Warwick, Coventry, Warwickshire, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5102-6564","authenticated-orcid":false,"given":"Jatinder","family":"Singh","sequence":"additional","affiliation":[{"name":"Research Centre Trust, UA Ruhr, University Duisburg-Essen, Duisburg, Germany and Department of Computer Science & Technology, University of Cambridge, Cambridge, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_2_2_2","volume-title":"Overview of the Code of Practice | EU Artificial Intelligence Act \u2014 artificialintelligenceact.eu","author":"Act EU\u00a0Artificial\u00a0Intelligence","year":"2025","unstructured":"EU\u00a0Artificial\u00a0Intelligence Act. 2025. Overview of the Code of Practice | EU Artificial Intelligence Act \u2014 artificialintelligenceact.eu. https:\/\/artificialintelligenceact.eu\/code-of-practice-overview\/ [Accessed 20-11-2025]."},{"key":"e_1_3_3_2_3_2","unstructured":"Saleh Afroogh Kush\u00a0R. Varshney and Jason D\u2019Cruz. 2025. A Task-Driven Human-AI Collaboration: When to Automate When to Collaborate When to Challenge. arxiv:https:\/\/arXiv.org\/abs\/2505.18422\u00a0[cs.CY] https:\/\/arxiv.org\/abs\/2505.18422"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Heather Akin Michael\u00a0A. Cacciatore Sara\u00a0K. Yeo Dominique Brossard Dietram\u00a0A. Scheufele and Michael\u00a0A. Xenos. 2020. Publics\u2019 Support for Novel and Established Science Issues Linked to Perceived Knowledge and Deference to Science. International Journal of Public Opinion Research 33 2 (06 2020) 422\u2013431. arXiv:https:\/\/academic.oup.com\/ijpor\/article-pdf\/33\/2\/422\/39770156\/edaa010.pdf10.1093\/ijpor\/edaa010","DOI":"10.1093\/ijpor\/edaa010"},{"key":"e_1_3_3_2_5_2","first-page":"24","volume-title":"SIGBOVIK : A Record of the Proceedings of SIGBOVIK 2025","author":"Andersson Vivi","year":"2025","unstructured":"Vivi Andersson, Benoit Baudry, Sofia Bobadilla, Ludvig Christensen, Serena Cofano, Khashayar Etemadi, Raphina Liu, Martin Monperrus, Frank Reyes\u00a0Garc\u00eda, Javier Ron\u00a0Arteaga, Aman Sharma, Deepika Tiwari, and Tim Toady. 2025. UPPERCASE IS ALL YOU NEED. In SIGBOVIK : A Record of the Proceedings of SIGBOVIK 2025. SIGBOVIK, 24\u201335. https:\/\/sigbovik.org\/2025\/proceedings.pdf"},{"key":"e_1_3_3_2_6_2","unstructured":"Anthropic. 2025. Configuring and Using Styles | Claude Help Center \u2014 support.claude.com. https:\/\/support.claude.com\/en\/articles\/10181068-configuring-and-using-styles [Accessed 26-11-2025]."},{"key":"e_1_3_3_2_7_2","volume-title":"Giving Claude a role with a system prompt - Anthropic \u2014 docs.anthropic.com","year":"2025","unstructured":"Anthropic. 2025. Giving Claude a role with a system prompt - Anthropic \u2014 docs.anthropic.com. Anthropic. https:\/\/docs.anthropic.com\/en\/docs\/build-with-claude\/prompt-engineering\/system-prompts [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642016"},{"key":"e_1_3_3_2_9_2","unstructured":"Yuntao Bai Andy Jones Kamal Ndousse Amanda Askell Anna Chen Nova DasSarma Dawn Drain Stanislav Fort Deep Ganguli Tom Henighan Nicholas Joseph Saurav Kadavath Jackson Kernion Tom Conerly Sheer El-Showk Nelson Elhage Zac Hatfield-Dodds Danny Hernandez Tristan Hume Scott Johnston Shauna Kravec Liane Lovitt Neel Nanda Catherine Olsson Dario Amodei Tom Brown Jack Clark Sam McCandlish Chris Olah Ben Mann and Jared Kaplan. 2022. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arxiv:https:\/\/arXiv.org\/abs\/2204.05862\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2204.05862"},{"key":"e_1_3_3_2_10_2","unstructured":"Yuntao Bai Saurav Kadavath Sandipan Kundu Amanda Askell Jackson Kernion Andy Jones Anna Chen Anna Goldie Azalia Mirhoseini Cameron McKinnon Carol Chen Catherine Olsson Christopher Olah Danny Hernandez Dawn Drain Deep Ganguli Dustin Li Eli Tran-Johnson Ethan Perez Jamie Kerr Jared Mueller Jeffrey Ladish Joshua Landau Kamal Ndousse Kamile Lukosuite Liane Lovitt Michael Sellitto Nelson Elhage Nicholas Schiefer Noemi Mercado Nova DasSarma Robert Lasenby Robin Larson Sam Ringer Scott Johnston Shauna Kravec Sheer\u00a0El Showk Stanislav Fort Tamera Lanham Timothy Telleen-Lawton Tom Conerly Tom Henighan Tristan Hume Samuel\u00a0R. Bowman Zac Hatfield-Dodds Ben Mann Dario Amodei Nicholas Joseph Sam McCandlish Tom Brown and Jared Kaplan. 2022. Constitutional AI: Harmlessness from AI Feedback. arxiv:https:\/\/arXiv.org\/abs\/2212.08073\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2212.08073"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3678884.3681831"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713787"},{"key":"e_1_3_3_2_13_2","unstructured":"Behavioural Insights Team. 2017. Helping more people take up free pension guidance: new results. https:\/\/www.bi.team\/blogs\/helping-more-people-take-up-free-pension-guidance-new-results\/ Accessed: 2025-08-30."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642406"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580651"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594019"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533083"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML59370.2024.00037"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Edyta Bogucka Marios Constantinides Sanja \u0160\u0107epanovi\u0107 and Daniele Quercia. 2024. Co-designing an AI Impact Assessment Report Template with AI Practitioners and AI Compliance Experts. Proceedings of the AAAI\/ACM Conference on AI Ethics and Society 7 1 (Oct. 2024) 168\u2013180. 10.1609\/aies.v7i1.31627","DOI":"10.1609\/aies.v7i1.31627"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Edyta\u00a0Paulina Bogucka Marios Constantinides Sanja \u0160\u0107epanovi\u0107 and Daniele Quercia. 2025. Impact Assessment Card: Communicating Risks and Benefits of AI Uses. Proceedings of the ACM on Human-Computer Interaction 9 7 (Oct. 2025) 1\u201342. 10.1145\/3757482","DOI":"10.1145\/3757482"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","unstructured":"Rishi Bommasani Kevin Klyman Shayne Longpre Betty Xiong Sayash Kapoor Nestor Maslej Arvind Narayanan and Percy Liang. 2024. Foundation Model Transparency Reports. Proceedings of the AAAI\/ACM Conference on AI Ethics and Society 7 1 (Oct. 2024) 181\u2013195. 10.1609\/aies.v7i1.31628","DOI":"10.1609\/aies.v7i1.31628"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Maarten Buyl Alexander Rogiers Sander Noels Guillaume Bied Iris Dominguez-Catena Edith Heiter Iman Johary Alexandru-Cristian Mara Rapha\u00ebl Romero Jefrey Lijffijt et\u00a0al. 2026. Large language models reflect the ideology of their creators. npj Artificial Intelligence 2 1 (2026) 7.","DOI":"10.1038\/s44387-025-00048-0"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659037"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445872"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Shreyas Chaudhari Pranjal Aggarwal Vishvak Murahari Tanmay Rajpurohit Ashwin Kalyan Karthik Narasimhan Ameet Deshpande and Bruno Castro\u00a0da Silva. 2025. Rlhf deciphered: A critical analysis of reinforcement learning from human feedback for llms. Comput. Surveys 58 2 (2025) 1\u201337.","DOI":"10.1145\/3743127"},{"key":"e_1_3_3_2_26_2","unstructured":"Runjin Chen Andy Arditi Henry Sleight Owain Evans and Jack Lindsey. 2025. Persona Vectors: Monitoring and Controlling Character Traits in Language Models. arxiv:https:\/\/arXiv.org\/abs\/2507.21509\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2507.21509"},{"key":"e_1_3_3_2_27_2","unstructured":"Yumin Choi Jinheon Baek and Sung\u00a0Ju Hwang. 2025. System Prompt Optimization with Meta-Learning. arxiv:https:\/\/arXiv.org\/abs\/2505.09666\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2505.09666"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732206"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445921"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594073"},{"key":"e_1_3_3_2_31_2","unstructured":"Rimom Costa. 2025. Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.00251 (2025)."},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533108"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Adam Dahlgren\u00a0Lindstr\u00f6m Leila Methnani Lea Krause Petter Ericson \u00cd\u00f1igo\u00a0Mart\u00ednez de\u00a0Rituerto\u00a0de Troya Dimitri Coelho\u00a0Mollo and Roel Dobbe. 2025. Helpful harmless honest? Sociotechnical limits of AI alignment and safety through Reinforcement Learning from Human Feedback: AD Lindstr\u00f6m et al. Ethics and Information Technology 27 2 (2025) 28.","DOI":"10.1007\/s10676-025-09837-2"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580969"},{"key":"e_1_3_3_2_35_2","unstructured":"DeepL. 2025. The DeepL API for translation and writing improvement at scale \u2014 deepl.com. https:\/\/www.deepl.com\/en\/products\/api [Accessed 30-01-2026]."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732118"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Yi Dong Ronghui Mu Yanghao Zhang Siqi Sun Tianle Zhang Changshun Wu Gaojie Jin Yi Qi Jinwei Hu Jie Meng et\u00a0al. 2025. Safeguarding large language models: A survey. Artificial intelligence review 58 12 (2025) 382.","DOI":"10.1007\/s10462-025-11389-2"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445188"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650750"},{"key":"e_1_3_3_2_40_2","unstructured":"Hugging Face. 2025. . https:\/\/huggingface.co\/blog\/codelion\/system-prompt-learning"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713477"},{"key":"e_1_3_3_2_42_2","unstructured":"Patrick Farley. 2025. Safety system message templates - Azure OpenAI in Azure AI Foundry Models \u2014 learn.microsoft.com. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-foundry\/openai\/concepts\/safety-system-message-templates [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Heike Felzmann Eduard Fosch-Villaronga Christoph Lutz and Aurelia Tam\u00f2-Larrieux. 2020. Towards Transparency by Design for Artificial Intelligence. Science and Engineering Ethics 26 6 (Dec. 2020) 3333\u20133361. 10.1007\/s11948-020-00276-4","DOI":"10.1007\/s11948-020-00276-4"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"Luciano Floridi Josh Cowls Thomas\u00a0C. King and Mariarosaria Taddeo. 2020. How to Design AI for Social Good: Seven Essential Factors. Science and Engineering Ethics 26 3 (June 2020) 1771\u20131796. 10.1007\/s11948-020-00213-5","DOI":"10.1007\/s11948-020-00213-5"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Batya Friedman. 1996. Value-sensitive design. interactions 3 6 (1996) 16\u201323.","DOI":"10.1145\/242485.242493"},{"key":"e_1_3_3_2_46_2","unstructured":"Tingchen Fu Jiawei Gu Yafu Li Xiaoye Qu and Yu Cheng. 2025. Scaling Reasoning Losing Control: Evaluating Instruction Following in Large Reasoning Models. arxiv:https:\/\/arXiv.org\/abs\/2505.14810\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2505.14810"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"crossref","unstructured":"Iason Gabriel. 2020. Artificial intelligence values and alignment. Minds and machines 30 3 (2020) 411\u2013437.","DOI":"10.1007\/s11023-020-09539-2"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Iason Gabriel and Vafa Ghazavi. 2022. The challenge of value alignment. The Oxford handbook of digital ethics (2022) 336\u2013355.","DOI":"10.1093\/oxfordhb\/9780198857815.013.18"},{"key":"e_1_3_3_2_49_2","unstructured":"Yilin Geng Haonan Li Honglin Mu Xudong Han Timothy Baldwin Omri Abend Eduard Hovy and Lea Frermann. 2025. Control Illusion: The Failure of Instruction Hierarchies in Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2502.15851\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2502.15851"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-68024-3_3"},{"key":"e_1_3_3_2_51_2","unstructured":"Australian Government. 2025. AI Technical Standard: Statement 7 | digital.gov.au. https:\/\/www.digital.gov.au\/policy\/ai\/AI-technical-standard\/ai-technical-standard-statement-7"},{"key":"e_1_3_3_2_52_2","volume-title":"@grok | Update on where has @grok been and what happened on July 8th.","year":"2025","unstructured":"Grok. 2025. @grok | Update on where has @grok been and what happened on July 8th.https:\/\/x.com\/grok\/status\/1943916977481036128"},{"key":"e_1_3_3_2_53_2","unstructured":"Maarten\u00a0P. Grootendorst. 2024. Best Practices - BERTopic \u2014 maartengr.github.io. https:\/\/maartengr.github.io\/BERTopic\/getting_started\/best_practices\/best_practices.html [Accessed 06-09-2025]."},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651042"},{"key":"e_1_3_3_2_55_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gupta Shashank","year":"2024","unstructured":"Shashank Gupta, Vaishnavi Shrivastava, Ameet Deshpande, Ashwin Kalyan, Peter Clark, Ashish Sabharwal, and Tushar Khot. 2024. Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=kGteeZ18Ir"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642472"},{"key":"e_1_3_3_2_57_2","unstructured":"Chi Han. 2025. Can Language Models Follow Multiple Turns of Entangled Instructions? arxiv:https:\/\/arXiv.org\/abs\/2503.13222\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2503.13222"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642133"},{"key":"e_1_3_3_2_59_2","unstructured":"Jia He Mukund Rungta David Koleczek Arshdeep Sekhon Franklin\u00a0X Wang and Sadid Hasan. 2024. Does Prompt Formatting Have Any Impact on LLM Performance? arxiv:https:\/\/arXiv.org\/abs\/2411.10541\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2411.10541"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"crossref","unstructured":"Leah Henrickson and Albert Mero\u00f1o-Pe\u00f1uela. 2025. Prompting meaning: a hermeneutic approach to optimising prompt engineering with ChatGPT. AI & SOCIETY 40 2 (2025) 903\u2013918.","DOI":"10.1007\/s00146-023-01752-8"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"publisher","unstructured":"Tomasz Hollanek. 2024. The Ethico-Politics of Design Toolkits: Responsible AI Tools From Big Tech Guidelines to Feminist Ideation Cards (Extended Abstract). Proceedings of the AAAI\/ACM Conference on AI Ethics and Society 7 1 (Oct. 2024) 610\u2013610. 10.1609\/aies.v7i1.31663","DOI":"10.1609\/aies.v7i1.31663"},{"key":"e_1_3_3_2_62_2","first-page":"1266","volume-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society","volume":"8","author":"Hopkins Aspen","year":"2025","unstructured":"Aspen Hopkins, Sarah\u00a0H Cen, Isabella Struckman, Andrew Ilyas, Luis Videgaray, and Aleksander M\u0105dry. 2025. Ai supply chains: An emerging ecosystem of ai actors, products, and services. In Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society , Vol.\u00a08. 1266\u20131277."},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732017"},{"key":"e_1_3_3_2_64_2","unstructured":"Peter Hoskins and Charlotte Edwards. 2025. Musk says Grok chatbot was \u2019manipulated\u2019 into praising Hitler \u2014 bbc.com. https:\/\/www.bbc.com\/news\/articles\/c4g8r34nxeno [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_65_2","unstructured":"White House. 2025. Preventing Woke AI in the Federal Government \u2014 whitehouse.gov. https:\/\/www.whitehouse.gov\/presidential-actions\/2025\/07\/preventing-woke-ai-in-the-federal-government\/ [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658979"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732154"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519833"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732002"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533097"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3534637"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","unstructured":"Jiaming Ji Tianyi Qiu Boyuan Chen Borong Zhang Hantao Lou Kaile Wang Yawen Duan Zhonghao He Jiayi Zhou Zhaowei Zhang Fanzhi Zeng Kwan\u00a0Yee Ng Juntao Dai Xuehai Pan Aidan O\u2019Gara Yingshan Lei Hua Xu Brian Tse Jie Fu Stephen McAleer Yaodong Yang Yizhou Wang Song-Chun Zhu Yike Guo and Wen Gao. 2023. AI Alignment: A Comprehensive Survey. CoRR abs\/2310.19852 (2023). 10.48550\/arXiv.2310.19852","DOI":"10.48550\/arXiv.2310.19852"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732069"},{"key":"e_1_3_3_2_74_2","unstructured":"Sheer Karny Anthony Baez and Pat Pataranutaporn. 2025. Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI. arxiv:https:\/\/arXiv.org\/abs\/2511.00230\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2511.00230"},{"key":"e_1_3_3_2_75_2","volume-title":"X Post","author":"Karpathy Andrej","year":"2025","unstructured":"Andrej Karpathy. 2025. X Post. https:\/\/x.com\/karpathy\/status\/1921368644069765486"},{"key":"e_1_3_3_2_76_2","first-page":"670","volume-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society","volume":"7","author":"Kawakami Anna","year":"2024","unstructured":"Anna Kawakami, Daricia Wilkinson, and Alexandra Chouldechova. 2024. Do responsible AI artifacts advance stakeholder goals? four key barriers perceived by legal and civil stakeholders. In Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society , Vol.\u00a07. 670\u2013682."},{"key":"e_1_3_3_2_77_2","unstructured":"Dara Kerr. 2025. Musk\u2019s AI Grok bot rants about \u2018white genocide\u2019 in South Africa in unrelated chats \u2014 theguardian.com. https:\/\/www.theguardian.com\/technology\/2025\/may\/14\/elon-musk-grok-white-genocide [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732147"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732147"},{"key":"e_1_3_3_2_80_2","unstructured":"John Koetsier. 2025. GPT-5\u2019s System Prompt Just Leaked. Here\u2019s What We Learned \u2014 forbes.com. https:\/\/www.forbes.com\/sites\/johnkoetsier\/2025\/08\/09\/gpt-5s-system-prompt-just-leaked-heres-what-we-learned\/ [Accessed 10-09-2025]."},{"key":"e_1_3_3_2_81_2","unstructured":"Tomek Korbak Mikita Balesni Elizabeth Barnes Yoshua Bengio Joe Benton Joseph Bloom Mark Chen Alan Cooney Allan Dafoe Anca Dragan Scott Emmons Owain Evans David Farhi Ryan Greenblatt Dan Hendrycks Marius Hobbhahn Evan Hubinger Geoffrey Irving Erik Jenner Daniel Kokotajlo Victoria Krakovna Shane Legg David Lindner David Luan Aleksander M\u0105dry Julian Michael Neel Nanda Dave Orr Jakub Pachocki Ethan Perez Mary Phuong Fabien Roger Joshua Saxe Buck Shlegeris Mart\u00edn Soto Eric Steinberger Jasmine Wang Wojciech Zaremba Bowen Baker Rohin Shah and Vlad Mikulik. 2025. Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety. arxiv:https:\/\/arXiv.org\/abs\/2507.11473\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2507.11473"},{"key":"e_1_3_3_2_82_2","doi-asserted-by":"crossref","unstructured":"Anton Korinek and Avital Balwit. 2022. Aligned with Whom? Direct and social goals for AI systems. arxiv:https:\/\/arXiv.org\/abs\/2205.04279\u00a0[cs.CY] https:\/\/arxiv.org\/abs\/2205.04279","DOI":"10.3386\/w30017"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"crossref","unstructured":"Kimberly\u00a0D Krawiec. 2003. Cosmetic compliance and the failure of negotiated governance. Wash. ULQ 81 (2003) 487.","DOI":"10.2139\/ssrn.448221"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445937"},{"key":"e_1_3_3_2_85_2","unstructured":"Genki Kusano Kosuke Akimoto and Kunihiro Takeoka. 2024. Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems. arxiv:https:\/\/arXiv.org\/abs\/2412.14454\u00a0[cs.IR] https:\/\/arxiv.org\/abs\/2412.14454"},{"key":"e_1_3_3_2_86_2","volume-title":"NeurIPS 2025 Workshop on Algorithmic Collective Action","author":"Kyi Lin","year":"2025","unstructured":"Lin Kyi, Paul G\u00f6lz, Asia Biega, and Robin Berjon. 2025. From Clicks to Consensus: A Collective Consent Approach to Online Privacy. In NeurIPS 2025 Workshop on Algorithmic Collective Action."},{"key":"e_1_3_3_2_87_2","unstructured":"Philippe Laban Hiroaki Hayashi Yingbo Zhou and Jennifer Neville. 2025. LLMs Get Lost In Multi-Turn Conversation. arxiv:https:\/\/arXiv.org\/abs\/2505.06120\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2505.06120"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642830"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"publisher","unstructured":"Shun\u00a0Yin Lam Jeongwen Chiang and A. Parasuraman. 2008. The effects of the dimensions of technology readiness on technology acceptance: An empirical analysis. Journal of Interactive Marketing 22 4 (2008) 19\u201339. 10.1002\/dir.20119","DOI":"10.1002\/dir.20119"},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"crossref","unstructured":"Jusil Lee. 2017. Why have policies often remained symbolic? Understanding the reasons for decoupling between policy and practice. Review of Policy Research 34 5 (2017) 617\u2013635.","DOI":"10.1111\/ropr.12241"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"crossref","unstructured":"Seongyun Lee Sue\u00a0Hyun Park Seungone Kim and Minjoon Seo. 2024. Aligning to thousands of preferences via system message generalization. Advances in Neural Information Processing Systems 37 (2024) 73783\u201373829.","DOI":"10.52202\/079017-2347"},{"key":"e_1_3_3_2_92_2","unstructured":"Ang Li Haozhe Chen Hongseok Namkoong and Tianyi Peng. 2025. LLM Generated Persona is a Promise with a Catch. arxiv:https:\/\/arXiv.org\/abs\/2503.16527\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2503.16527"},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","unstructured":"Zixi Li Jingyuan Shi Yinqiao Zhao Bohan Zhang and Bu Zhong. 2024. Indirect Media Effects on the Adoption of Artificial Intelligence: The Roles of Perceived and Actual Knowledge in the Influence of Presumed Media Influence Model. Journal of Broadcasting & Electronic Media 68 4 (2024) 581\u2013600. arXiv:10.1080\/08838151.2024.237724410.1080\/08838151.2024.2377244","DOI":"10.1080\/08838151.2024.2377244"},{"key":"e_1_3_3_2_94_2","unstructured":"Qibang Liu Wenzhe Wang and Jeffrey Willard. 2025. Effects of Prompt Length on Domain-specific Tasks for Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2502.14255\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2502.14255"},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642840"},{"key":"e_1_3_3_2_96_2","unstructured":"Emily Long. 2025. Your AI Browser May Be Vulnerable to \u2019Prompt Injection\u2019 Attacks \u2014 lifehacker.com. https:\/\/lifehacker.com\/tech\/prompt-injection-attacks-ai-browsers [Accessed 10-09-2025]."},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533161"},{"key":"e_1_3_3_2_98_2","doi-asserted-by":"crossref","unstructured":"Pedro\u00a0Henrique Luz\u00a0de Araujo and Benjamin Roth. 2025. Helpful assistant or fruitful facilitator? Investigating how personas affect language model behavior. PloS one 20 6 (2025) e0325664.","DOI":"10.1371\/journal.pone.0325664"},{"key":"e_1_3_3_2_99_2","unstructured":"Aengus Lynch Benjamin Wright Caleb Larson Kevin\u00a0K. Troy Stuart\u00a0J. Ritchie S\u00f6ren Mindermann Ethan Perez and Evan Hubinger. 2025. Agentic Misalignment: How LLMs Could be an Insider Threat. Anthropic Research (2025). https:\/\/www.anthropic.com\/research\/agentic-misalignment."},{"key":"e_1_3_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713540"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651100"},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658988"},{"key":"e_1_3_3_2_103_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642861"},{"key":"e_1_3_3_2_104_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642861"},{"key":"e_1_3_3_2_105_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650947"},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642462"},{"key":"e_1_3_3_2_107_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i17.17817"},{"key":"e_1_3_3_2_108_2","unstructured":"Alexander Meinke Bronson Schoen J\u00e9r\u00e9my Scheurer Mikita Balesni Rusheb Shah and Marius Hobbhahn. 2025. Frontier Models are Capable of In-context Scheming. arxiv:https:\/\/arXiv.org\/abs\/2412.04984\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2412.04984"},{"key":"e_1_3_3_2_109_2","unstructured":"Dan Milmo. 2025. Elon Musk\u2019s AI firm blames unauthorised change for chatbot\u2019s rant about \u2018white genocide\u2019 \u2014 theguardian.com. https:\/\/www.theguardian.com\/technology\/2025\/may\/16\/elon-musks-ai-firm-blames-unauthorised-change-for-chatbots-rant-about-white-genocide [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_3_2_111_2","unstructured":"Norman Mu Jonathan Lu Michael Lavery and David Wagner. 2025. A Closer Look at System Prompt Robustness. arxiv:https:\/\/arXiv.org\/abs\/2502.12197\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2502.12197"},{"key":"e_1_3_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732038"},{"key":"e_1_3_3_2_113_2","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594093"},{"key":"e_1_3_3_2_114_2","doi-asserted-by":"publisher","unstructured":"Helen Nissenbaum. 2011. A Contextual Approach to Privacy Online. Daedalus 140 (10 2011) 32\u201348. 10.1162\/DAED_a_00113","DOI":"10.1162\/DAED_a_00113"},{"key":"e_1_3_3_2_115_2","doi-asserted-by":"crossref","unstructured":"NIST. 2023. Artificial intelligence risk management framework (AI RMF 1.0). URL: https:\/\/nvlpubs.nist.gov\/nistpubs\/ai\/nist.ai (2023).","DOI":"10.6028\/NIST.AI.100-1.jpn"},{"key":"e_1_3_3_2_116_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533133"},{"key":"e_1_3_3_2_117_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533133"},{"key":"e_1_3_3_2_118_2","unstructured":"OpenAI. 2023. Custom instructions for ChatGPT \u2014 openai.com. https:\/\/openai.com\/index\/custom-instructions-for-chatgpt\/ [Accessed 26-11-2025]."},{"key":"e_1_3_3_2_119_2","volume-title":"Introducing GPTs \u2014 openai.com","year":"2023","unstructured":"OpenAI. 2023. Introducing GPTs \u2014 openai.com. https:\/\/openai.com\/index\/introducing-gpts\/ [Accessed 08-09-2025]."},{"key":"e_1_3_3_2_120_2","volume-title":"OpenAI Model Spec \u2014 model-spec.openai.com","year":"2025","unstructured":"OpenAI. 2025. OpenAI Model Spec \u2014 model-spec.openai.com. https:\/\/model-spec.openai.com\/2025-04-11.html [Accessed 06-09-2025]."},{"key":"e_1_3_3_2_121_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533235"},{"key":"e_1_3_3_2_122_2","doi-asserted-by":"publisher","unstructured":"Yulu Pi and Maddie Proctor. 2025. Toward empowering AI governance with redress mechanisms. Cambridge Forum on AI: Law and Governance 1 (05 2025). 10.1017\/cfl.2025.9","DOI":"10.1017\/cfl.2025.9"},{"key":"e_1_3_3_2_123_2","unstructured":"NLTK Project. 2023. NLTK :: nltk.tokenize.sent_tokenize \u2014 nltk.org. https:\/\/www.nltk.org\/api\/nltk.tokenize.sent_tokenize.html [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533231"},{"key":"e_1_3_3_2_125_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Qi Xiangyu","year":"2024","unstructured":"Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen, Ruoxi Jia, Prateek Mittal, and Peter Henderson. 2024. Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=hTEGyKf0dZ"},{"key":"e_1_3_3_2_126_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714051"},{"key":"e_1_3_3_2_127_2","unstructured":"Brandon Roberts and Vernal Coleman. 2025. Inside the AI Prompts DOGE Used to \u201cMunch\u201d Contracts Related to Veterans\u2019 Health \u2014 propublica.org. https:\/\/www.propublica.org\/article\/inside-ai-tool-doge-veterans-affairs-contracts-sahil-lavingia [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_128_2","unstructured":"Nick Robins-Early and Lauren Gambino. 2025. Trump signs executive orders targeting \u2018woke\u2019 AI models and regulation \u2014 theguardian.com. https:\/\/www.theguardian.com\/us-news\/2025\/jul\/23\/trump-executive-orders-woke-ai [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_129_2","unstructured":"Julian Rodemann Esteban\u00a0Garces Arias Christoph Luther Christoph Jansen and Thomas Augustin. 2025. A Statistical Case Against Empirical Human-AI Alignment. ArXiv abs\/2502.14581 (2025). https:\/\/api.semanticscholar.org\/CorpusID:276482206"},{"key":"e_1_3_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533239"},{"key":"e_1_3_3_2_131_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642810"},{"key":"e_1_3_3_2_132_2","doi-asserted-by":"crossref","unstructured":"Malak Sadek Emma Kallina Thomas Bohn\u00e9 C\u00e9line Mougenot Rafael\u00a0A Calvo and Stephen Cave. 2025. Challenges of responsible AI in practice: scoping review and recommended actions. AI & SOCIETY 40 1 (2025) 199\u2013215.","DOI":"10.1007\/s00146-024-01880-9"},{"key":"e_1_3_3_2_133_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659032"},{"key":"e_1_3_3_2_134_2","doi-asserted-by":"publisher","unstructured":"Astrid Schepman and Paul Rodway. 2020. Initial validation of the general attitudes towards Artificial Intelligence Scale. Computers in Human Behavior Reports 1 (2020) 100014. 10.1016\/j.chbr.2020.100014","DOI":"10.1016\/j.chbr.2020.100014"},{"key":"e_1_3_3_2_135_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658971"},{"key":"e_1_3_3_2_136_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642531"},{"key":"e_1_3_3_2_137_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642531"},{"key":"e_1_3_3_2_138_2","doi-asserted-by":"publisher","unstructured":"Sander Schulhoff Michael Ilie Nishant Balepur Konstantine Kahadze Amanda Liu Chenglei Si Yinheng Li Aayush Gupta HyoJung Han Sevien Schulhoff Pranav\u00a0Sandeep Dulepet Saurav Vidyadhara Dayeon Ki Sweta Agrawal Chau Pham Gerson\u00a0C. Kroiz Feileen Li Hudson Tao Ashay Srivastava Hevander\u00a0Da Costa Saloni Gupta Megan\u00a0L. Rogers Inna Goncearenco Giuseppe Sarli Igor Galynker Denis Peskoff Marine Carpuat Jules White Shyamal Anadkat Alexander\u00a0Miserlis Hoyle and Philip Resnik. 2024. The Prompt Report: A Systematic Survey of Prompting Techniques. CoRR abs\/2406.06608 (2024). 10.48550\/arXiv.2406.06608","DOI":"10.48550\/arXiv.2406.06608"},{"key":"e_1_3_3_2_139_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sclar Melanie","year":"2024","unstructured":"Melanie Sclar, Yejin Choi, Yulia Tsvetkov, and Alane Suhr. 2024. Quantifying Language Models\u2019 Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=RIu5lyNXjT"},{"key":"e_1_3_3_2_140_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445971"},{"key":"e_1_3_3_2_141_2","unstructured":"Amanda Silberling. 2025. X takes Grok offline changes system prompts after more antisemitic outbursts | TechCrunch \u2014 techcrunch.com. https:\/\/techcrunch.com\/2025\/07\/09\/x-takes-grok-offline-changes-system-prompts-after-more-antisemitic-outbursts\/ [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_142_2","doi-asserted-by":"publisher","unstructured":"Jatinder Singh Jennifer Cobbe and Chris Norval. 2019. Decision Provenance: Harnessing Data Flow for Accountable Systems. IEEE Access 7 (2019) 6562\u20136574. 10.1109\/ACCESS.2018.2887201","DOI":"10.1109\/ACCESS.2018.2887201"},{"key":"e_1_3_3_2_143_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732167"},{"key":"e_1_3_3_2_144_2","series-title":"(ICML\u201924)","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Sorensen Taylor","year":"2024","unstructured":"Taylor Sorensen, Jared Moore, Jillian Fisher, Mitchell Gordon, Niloofar Mireshghallah, Christopher\u00a0Michael Rytting, Andre Ye, Liwei Jiang, Ximing Lu, Nouha Dziri, Tim Althoff, and Yejin Choi. 2024. Position: a roadmap to pluralistic alignment. In Proceedings of the 41st International Conference on Machine Learning (Vienna, Austria) (ICML\u201924). JMLR.org, Article 1882, 23\u00a0pages."},{"key":"e_1_3_3_2_145_2","doi-asserted-by":"crossref","unstructured":"Bernd\u00a0Carsten Stahl Josephina Antoniou Nitika Bhalla Laurence Brooks Philip Jansen Blerta Lindqvist Alexey Kirichenko Samuel Marchal Rowena Rodrigues Nicole Santiago et\u00a0al. 2023. A systematic review of artificial intelligence impact assessments. Artificial Intelligence Review 56 11 (2023) 12799\u201312831.","DOI":"10.1007\/s10462-023-10420-8"},{"key":"e_1_3_3_2_146_2","unstructured":"Ben Stewart. [n. d.]. stm: An R Package for Structural Topic Models.https:\/\/github.com\/bstewart\/stm\/blob\/7750a9112159625d8e2514b4139fc1099925460c\/R\/stm.R [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_147_2","doi-asserted-by":"publisher","unstructured":"Jack Stilgoe. 2024. AI has a democracy problem. Citizens\u2019 assemblies can help. Science 385 6711 (2024) eadr6713. arXiv:https:\/\/www.science.org\/doi\/pdf\/10.1126\/science.adr671310.1126\/science.adr6713","DOI":"10.1126\/science.adr6713"},{"key":"e_1_3_3_2_148_2","doi-asserted-by":"publisher","unstructured":"Jonathan Stray Alon Halevy Parisa Assar Dylan Hadfield-Menell Craig Boutilier Amar Ashar Chloe Bakalar Lex Beattie Michael Ekstrand Claire Leibowicz Connie Moon\u00a0Sehat Sara Johansen Lianne Kerlin David Vickrey Spandana Singh Sanne Vrijenhoek Amy Zhang McKane Andrus Natali Helberger Polina Proutskova Tanushree Mitra and Nina Vasan. 2024. Building Human Values into Recommender Systems: An Interdisciplinary Synthesis. ACM Transactions on Recommender Systems 2 3 (June 2024) 1\u201357. 10.1145\/3632297","DOI":"10.1145\/3632297"},{"key":"e_1_3_3_2_149_2","unstructured":"Josh Taylor. 2025. Musk\u2019s AI firm forced to delete posts praising Hitler from Grok chatbot \u2014 theguardian.com. https:\/\/www.theguardian.com\/technology\/2025\/jul\/09\/grok-ai-praised-hitler-antisemitism-x-ntwnfb [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_150_2","doi-asserted-by":"crossref","unstructured":"Gareth Terry Nikki Hayfield Victoria Clarke Virginia Braun et\u00a0al. 2017. Thematic analysis. The SAGE handbook of qualitative research in psychology 2 17-37 (2017) 25.","DOI":"10.4135\/9781526405555.n2"},{"key":"e_1_3_3_2_151_2","volume-title":"NUDGE: Improving Decisions About Health, Wealth, and Happiness","author":"Thaler Richard","year":"2009","unstructured":"Richard Thaler and C. Sunstein. 2009. NUDGE: Improving Decisions About Health, Wealth, and Happiness. Vol.\u00a047. Journal Abbreviation: Nudge: Improving Decisions about Health, Wealth, and Happiness Publication Title: Nudge: Improving Decisions about Health, Wealth, and Happiness."},{"key":"e_1_3_3_2_152_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604700"},{"key":"e_1_3_3_2_153_2","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658985"},{"key":"e_1_3_3_2_154_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581387"},{"key":"e_1_3_3_2_155_2","doi-asserted-by":"crossref","unstructured":"Lena Ulbricht and Karen Yeung. 2022. Algorithmic regulation: A maturing concept for investigating regulation of and through algorithms. Regulation & Governance 16 1 (2022) 3\u201322.","DOI":"10.1111\/rego.12437"},{"key":"e_1_3_3_2_156_2","unstructured":"Lucas Valbuena. 2025. Over 12 000 Stars! \u2014 lucknitelol. https:\/\/medium.com\/@lucknitelol\/over-12-000-stars-42cf92d1cc4b [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_157_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372856"},{"key":"e_1_3_3_2_158_2","doi-asserted-by":"publisher","DOI":"10.1145\/3351095.3372856"},{"key":"e_1_3_3_2_159_2","unstructured":"Eric Wallace Kai Xiao Reimar Leike Lilian Weng Johannes Heidecke and Alex Beutel. 2024. The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions. arxiv:https:\/\/arXiv.org\/abs\/2404.13208\u00a0[cs.CR] https:\/\/arxiv.org\/abs\/2404.13208"},{"key":"e_1_3_3_2_160_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642466"},{"key":"e_1_3_3_2_161_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642135"},{"key":"e_1_3_3_2_162_2","unstructured":"Monica\u00a0J. White. 2025. \u2018You are ChatGPT\u2019: Leaked system prompt reveals the inner workings of GPT-5 \u2014 digitaltrends.com. https:\/\/www.digitaltrends.com\/computing\/you-are-chatgpt-leaked-system-prompt-reveals-the-inner-workings-of-gpt-5\/ [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_163_2","doi-asserted-by":"publisher","unstructured":"David\u00a0Gray Widder and Dawn Nafus. 2023. Dislocated accountabilities in the \u201cAI supply chain\u201d: Modularity and developers\u2019 notions of responsibility. Big Data & Society 10 1 (2023). arXiv:10.1177\/2053951723117762010.1177\/20539517231177620","DOI":"10.1177\/20539517231177620"},{"key":"e_1_3_3_2_164_2","unstructured":"David\u00a0Gray Widder and Richmond Wong. 2024. Thinking Upstream: Ethics and Policy Opportunities in AI Supply Chains. arxiv:https:\/\/arXiv.org\/abs\/2303.07529\u00a0[cs.CY] https:\/\/arxiv.org\/abs\/2303.07529"},{"key":"e_1_3_3_2_165_2","unstructured":"Simon Willison. 2025. Highlights from the Claude 4 system prompt \u2014 simonwillison.net. https:\/\/simonwillison.net\/2025\/May\/25\/claude-4-system-prompt\/ [Accessed 07-09-2025]."},{"key":"e_1_3_3_2_166_2","unstructured":"Mengke Wu Weizi Liu Yanyun Wang Weiyu Ding and Mike Yao. 2025. Rethinking User Empowerment in AI Recommender Systems: Designing through Transparency and Control. arxiv:https:\/\/arXiv.org\/abs\/2509.11098\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2509.11098"},{"key":"e_1_3_3_2_167_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719900"},{"key":"e_1_3_3_2_168_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719900"},{"key":"e_1_3_3_2_169_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3719900"},{"key":"e_1_3_3_2_170_2","volume-title":"Workshop on Reasoning and Planning for Large Language Models","author":"Wu Yuyang","year":"2025","unstructured":"Yuyang Wu, Yifei Wang, Tianqi Du, Stefanie Jegelka, and Yisen Wang. 2025. When More is Less: Understanding Chain-of-Thought Length in LLMs. In Workshop on Reasoning and Planning for Large Language Models. https:\/\/openreview.net\/forum?id=W8dxn7hBkO"},{"key":"e_1_3_3_2_171_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713626"},{"key":"e_1_3_3_2_172_2","doi-asserted-by":"publisher","DOI":"10.1145\/3715070.3749256"},{"key":"e_1_3_3_2_173_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_3_2_174_2","unstructured":"Marc Zao-Sanders. 2024. How people are really using genai. https:\/\/hbr.org\/2024\/03\/how-people-are-really-using-genai"},{"key":"e_1_3_3_2_175_2","unstructured":"Marc Zao-Sanders. 2025. How people are really using Gen AI in 2025. https:\/\/hbr.org\/2025\/04\/how-people-are-really-using-gen-ai-in-2025"},{"key":"e_1_3_3_2_176_2","unstructured":"Lily\u00a0Hong Zhang Smitha Milli Karen Jusko Jonathan Smith Brandon Amos Wassim Bouaziz Manon Revel Jack Kussman Lisa Titus Bhaktipriya Radharapu Jane Yu Vidya Sarma Kris Rose and Maximilian Nickel. 2025. Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset. arxiv:https:\/\/arXiv.org\/abs\/2507.09650\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2507.09650"},{"key":"e_1_3_3_2_177_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713293"},{"key":"e_1_3_3_2_178_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713110"},{"key":"e_1_3_3_2_179_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.425"},{"key":"e_1_3_3_2_180_2","volume-title":"ICLR Workshop: Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI","author":"Zhang Ze\u00a0Yu","year":"2025","unstructured":"Ze\u00a0Yu Zhang, Arun Verma, Finale Doshi-Velez, and Bryan Kian\u00a0Hsiang Low. 2025. Understanding the Relationship between Prompts and Response Uncertainty in Large Language Models. In ICLR Workshop: Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI. https:\/\/openreview.net\/forum?id=Z8E2JQW3QG"},{"key":"e_1_3_3_2_181_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.888"},{"key":"e_1_3_3_2_182_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.888"},{"key":"e_1_3_3_2_183_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zverev Egor","year":"2025","unstructured":"Egor Zverev, Sahar Abdelnabi, Soroush Tabesh, Mario Fritz, and Christoph\u00a0H. Lampert. 2025. Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=8EtSBX41mt"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3791726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T10:13:07Z","timestamp":1776247987000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791726"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":182,"alternative-id":["10.1145\/3772318.3791726","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791726","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}