{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T23:28:08Z","timestamp":1773617288880,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","funder":[{"name":"NSF CAREER","award":["2440198"],"award-info":[{"award-number":["2440198"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,22]]},"DOI":"10.1145\/3786304.3787891","type":"proceedings-article","created":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T23:43:22Z","timestamp":1772322202000},"page":"514-518","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Offscript: Agentic Auditing of Instruction Adherence in LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0098-9269","authenticated-orcid":false,"given":"Nicholas","family":"Clark","sequence":"first","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4837-7453","authenticated-orcid":false,"given":"Ryan","family":"Bai","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9507-6192","authenticated-orcid":false,"given":"Tanu","family":"Mitra","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, Washington, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"2025. ChatGPT Custom Instructions. https:\/\/help.openai.com\/en\/articles\/8096356-chatgpt-custom-instructions"},{"key":"e_1_3_3_1_3_2","unstructured":"2025. Get personalization in Gemini Apps - Android - Gemini Apps Help. https:\/\/support.google.com\/gemini\/answer\/15637730?hl=en&co=GENIE.Platform%3DAndroid"},{"key":"e_1_3_3_1_4_2","unstructured":"2025. Understanding Claude\u2019s Personalization Features | Anthropic Help Center. https:\/\/support.anthropic.com\/en\/articles\/10185728-understanding-claude-s-personalization-features"},{"key":"e_1_3_3_1_5_2","unstructured":"2025. Understanding Claude\u2019s Personalization Features | Claude Help Center. https:\/\/support.claude.com\/en\/articles\/10185728-understanding-claude-s-personalization-features"},{"key":"e_1_3_3_1_6_2","unstructured":"Ahmed Ahmed Kevin Klyman Yi Zeng Sanmi Koyejo and Percy Liang. 2025. SpecEval: Evaluating Model Adherence to Behavior Specifications. arxiv:https:\/\/arXiv.org\/abs\/2509.02464\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2509.02464"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Ram\u00f3n Alvarado. 2023. AI as an epistemic technology. Science and Engineering Ethics 29 5 (2023) 32.","DOI":"10.1007\/s11948-023-00451-3"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Jean\u00a0V Alves Diogo Leit\u00e3o S\u00e9rgio Jesus Marco\u00a0OP Sampaio Javier Li\u00e9bana Pedro Saleiro M\u00e1rio\u00a0AT Figueiredo and Pedro Bizarro. 2025. A benchmarking framework and dataset for learning to defer in human-AI decision-making. Scientific data 12 1 (2025) 506.","DOI":"10.1038\/s41597-025-04664-y"},{"key":"e_1_3_3_1_9_2","series-title":"(ICML\u201924)","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Chiang Wei-Lin","year":"2024","unstructured":"Wei-Lin Chiang, Lianmin Zheng, Ying Sheng, Anastasios\u00a0N. Angelopoulos, Tianle Li, Dacheng Li, Banghua Zhu, Hao Zhang, Michael\u00a0I. Jordan, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2024. Chatbot arena: an open platform for evaluating LLMs by human preference. In Proceedings of the 41st International Conference on Machine Learning (Vienna, Austria) (ICML\u201924). JMLR.org, Article 331, 30\u00a0pages."},{"key":"e_1_3_3_1_10_2","volume-title":"Second Conference on Language Modeling","author":"Clark Nicholas","year":"2025","unstructured":"Nicholas Clark, Hua Shen, Bill Howe, and Tanu Mitra. 2025. Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery. In Second Conference on Language Modeling. https:\/\/openreview.net\/forum?id=Orvjm9UqH2"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.240"},{"key":"e_1_3_3_1_12_2","unstructured":"Kai Fronsdal Isha Gupta Abhay Sheshadri Jonathan Michala Stephen McAleer Rowan Wang Sara Price and Sam Bowman. 2025. Petri: Parallel Exploration of Risky Interactions. https:\/\/github.com\/safety-research\/petri"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/237"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.301"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Barbara\u00a0K. Hofer. 2000. Dimensionality and Disciplinary Differences in Personal Epistemology. Contemporary Educational Psychology 25 4 (2000) 378\u2013405. 10.1006\/ceps.1999.1026","DOI":"10.1006\/ceps.1999.1026"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et\u00a0al. 2025. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. ACM Transactions on Information Systems 43 2 (2025) 1\u201355.","DOI":"10.1145\/3703155"},{"key":"e_1_3_3_1_17_2","volume-title":"Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning","author":"Jang Joel","unstructured":"Joel Jang, Seungone Kim, Bill\u00a0Yuchen Lin, Yizhong Wang, Jack Hessel, Luke Zettlemoyer, Hannaneh Hajishirzi, Yejin Choi, and Prithviraj Ammanabrolu. [n. d.]. Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging. In Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning."},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"crossref","unstructured":"Jinqi Lai Wensheng Gan Jiayang Wu Zhenlian Qi and Philip\u00a0S Yu. 2024. Large language models in law: A survey. AI Open 5 (2024) 181\u2013196.","DOI":"10.1016\/j.aiopen.2024.09.002"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0Richard Landis and Gary\u00a0G. Koch. 1977. The Measurement of Observer Agreement for Categorical Data. Biometrics 33 1 (1977) 159\u2013174. http:\/\/www.jstor.org\/stable\/2529310","DOI":"10.2307\/2529310"},{"key":"e_1_3_3_1_20_2","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar et\u00a0al. [n. d.]. Holistic Evaluation of Language Models. Transactions on Machine Learning Research ([n. d.])."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"e_1_3_3_1_22_2","unstructured":"Lei Liu Xiaoyan Yang Junchi Lei Xiaoyang Liu Yue Shen Zhiqiang Zhang Peng Wei Jinjie Gu Zhixuan Chu Zhan Qin et\u00a0al. 2024. A Survey on Medical Large Language Models: Technology Application Trustworthiness and Future Directions. CoRR (2024)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92611-2_5"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713301"},{"key":"e_1_3_3_1_25_2","unstructured":"Hua Shen Nicholas Clark and Tanushree Mitra. 2025. Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values? arxiv:https:\/\/arXiv.org\/abs\/2501.15463\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2501.15463"},{"key":"e_1_3_3_1_26_2","first-page":"46280","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, et\u00a0al. 2024. Position: a roadmap to pluralistic alignment. In Proceedings of the 41st International Conference on Machine Learning. 46280\u201346302."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Kwok wai Chan\u00a0* and Robert\u00a0G. Elliott. 2004. Epistemological beliefs across cultures: critique and analysis of beliefs structure studies. Educational Psychology 24 2 (2004) 123\u2013142. arXiv:10.1080\/014434103200016010010.1080\/0144341032000160100","DOI":"10.1080\/0144341032000160100"},{"key":"e_1_3_3_1_28_2","unstructured":"Shen Wang Tianlong Xu Hang Li Chaoli Zhang Joleen Liang Jiliang Tang Philip\u00a0S Yu and Qingsong Wen. 2024. Large language models for education: A survey and outlook. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.18105 (2024)."},{"key":"e_1_3_3_1_29_2","unstructured":"Zhehao Zhang Ryan\u00a0A. Rossi Branislav Kveton Yijia Shao Diyi Yang Hamed Zamani Franck Dernoncourt Joe Barrow Tong Yu Sungchul Kim Ruiyi Zhang Jiuxiang Gu Tyler Derr Hongjie Chen Junda Wu Xiang Chen Zichao Wang Subrata Mitra Nedim Lipka Nesreen\u00a0K. Ahmed and Yu Wang. 2025. Personalization of Large Language Models: A Survey. Transactions on Machine Learning Research (2025). https:\/\/openreview.net\/forum?id=tf6A9EYMo6 Survey Certification."}],"event":{"name":"CHIIR '26: 2026 ACM SIGIR Conference on Human Information Interaction and Retrieval","location":"Seattle USA","acronym":"CHIIR '26","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 2026 Conference on Human Information Interaction and Retrieval"],"original-title":[],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T22:45:38Z","timestamp":1773614738000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3786304.3787891"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":28,"alternative-id":["10.1145\/3786304.3787891","10.1145\/3786304"],"URL":"https:\/\/doi.org\/10.1145\/3786304.3787891","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}