{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:46:35Z","timestamp":1782758795980,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":409,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T00:00:00Z","timestamp":1782345600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,25]]},"DOI":"10.1145\/3805689.3806763","type":"proceedings-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T16:20:39Z","timestamp":1782231639000},"page":"6466-6509","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Prompt Governance? On Governing Technologies Governed by Natural Language"],"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\/0000-0003-3482-7789","authenticated-orcid":false,"given":"Holli","family":"Sargeant","sequence":"additional","affiliation":[{"name":"University of Cambridge, Cambridge, 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 University of Cambridge, Cambridge, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Adetayo Adebimpe Helmut Neukirchen and Thomas Welsh. 2025. SBASH: a Framework for Designing and Evaluating RAG vs. Prompt-Tuned LLM Honeypots. doi:10.48550\/arXiv.2510.21459","DOI":"10.48550\/arXiv.2510.21459"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.01518"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.94"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s41235-023-00529-3"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2025.107832"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-09694-4_16"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Ahmet Yusuf Alan Enis Karaarslan and Omer Aydin. 2025. Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAS. doi:10.48550\/arXiv.2401.15378","DOI":"10.48550\/arXiv.2401.15378"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2025.0160632"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.15769853"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3593990"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.arabicnlp-main.26"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Mina Almasi and Ross Deans Kristensen-McLachlan. 2025. Alignment Drift in CEFR-prompted LLMs for Interactive Spanish Tutoring. doi:10.48550\/arXiv.2505.08351","DOI":"10.48550\/arXiv.2505.08351"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-18011-7_3"},{"key":"e_1_3_2_1_14_1","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_2_1_15_1","unstructured":"Anthropic. 2025. Effective context engineering for AI agents \u2014 anthropic.com. https:\/\/www.anthropic.com\/engineering\/effective-context-engineering-for-ai-agents [Accessed 11-01-2026]."},{"key":"e_1_3_2_1_16_1","unstructured":"Anthropic. 2025. Giving Claude a role with a system prompt - Anthropic \u2014 docs.anthropic.com. https:\/\/docs.anthropic.com\/en\/docs\/build-with-claude\/prompt-engineering\/system-prompts [Accessed 07-09-2025]."},{"key":"e_1_3_2_1_17_1","unstructured":"Anthropic. 2026. Statement on the comments from Secretary of War Pete Hegseth \u2014 anthropic.com. https:\/\/www.anthropic.com\/news\/statement-comments-secretary-war [Accessed 17-03-2026]."},{"key":"e_1_3_2_1_18_1","unstructured":"Anthropic. 2026. Where things stand with the Department of War \u2014 anthropic.com. https:\/\/www.anthropic.com\/news\/where-stand-department-war [Accessed 17-03-2026]."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713248"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.3390\/act14090459"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.02709"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Suriya Ganesh Ayyamperumal and Limin Ge. 2024. Current state of LLM Risks and AI Guardrails. doi:10.48550\/arXiv.2406.12934","DOI":"10.48550\/arXiv.2406.12934"},{"key":"e_1_3_2_1_23_1","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:2204.05862 [cs.CL] https:\/\/arxiv.org\/abs\/2204.05862"},{"key":"e_1_3_2_1_24_1","unstructured":"Agathe Balayn Lorenzo Corti Fanny Rancourt Fabio Casati and Ujwal Gadiraju. 2024. Understanding Stakeholders' Perceptions and Needs Across the LLM Supply Chain. arXiv:2405.16311 [cs.HC] https:\/\/arxiv.org\/abs\/2405.16311"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Rick Battle and Teja Gollapudi. 2024. The Unreasonable Effectiveness of Eccentric Automatic Prompts. doi:10.48550\/arXiv.2402.10949","DOI":"10.48550\/arXiv.2402.10949"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5753\/sbgames.2025.10222"},{"key":"e_1_3_2_1_27_1","unstructured":"Rebecca Bellan. 2025. OpenAI adds new teen safety rules to ChatGPT as lawmakers weigh AI standards for minors | TechCrunch \u2014 techcrunch.com. https:\/\/techcrunch.com\/2025\/12\/19\/openai-adds-new-teen-safety-rules-to-models-as-lawmakers-weigh-ai-standards-for-minors\/ [Accessed 10-01-2026]."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.15891"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","unstructured":"Shir Bernstein David Beste Daniel Ayzenshteyn Lea Schonherr and Yisroel Mirsky. 2025. Trust Me I Know This Function: Hijacking LLM Static Analysis using Bias. doi:10.48550\/arXiv.2508.17361","DOI":"10.48550\/arXiv.2508.17361"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.01900"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533083"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML59370.2024.00037"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v12i1.31597"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.2196\/68426"},{"key":"e_1_3_2_1_35_1","volume-title":"The Brussels effect: How the European Union rules the world","author":"Bradford Anu","unstructured":"Anu Bradford. 2020. The Brussels effect: How the European Union rules the world. Oxford University Press."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"Christian Braun Alexander Lilienbeck and Daniel Mentjukov. 2025. The Hidden Structure - Improving Legal Document Understanding Through Explicit Text Formatting. doi:10.48550\/arXiv.2505.12837","DOI":"10.48550\/arXiv.2505.12837"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","unstructured":"Maarten Buyl Yousra Fettach Guillaume Bied and Tijl De Bie. 2025. Building and Measuring Trust between Large Language Models. doi:10.48550\/arXiv.2508.15858","DOI":"10.48550\/arXiv.2508.15858"},{"key":"e_1_3_2_1_38_1","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 and Tijl De Bie. 2025. Large Language Models Reflect the Ideology of their Creators. arXiv:2410.18417 [cs.CL] https:\/\/arxiv.org\/abs\/2410.18417","DOI":"10.1038\/s44387-025-00048-0"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/s44387-025-00048-0"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","unstructured":"Jinyu Cai Yusei Ishimizu Mingyue Zhang Munan Li Jialong Li and Kenji Tei. 2025. Simulation of Language Evolution under Regulated Social Media Platforms: A Synergistic Approach of Large Language Models and Genetic Algorithms. doi:10.48550\/arXiv.2502.19193","DOI":"10.48550\/arXiv.2502.19193"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3719027.3765124"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","unstructured":"Jeshwanth Challagundla Mantek Singh Siddharth Raina Smarth Behl FNU Harsh and Jasmin Jarsania. 2025. SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models. In 2025 16th International Conference on Information Intelligence Systems & Applications (IISA). 1\u20139. doi:10.1109\/IISA66859.2025.11311216","DOI":"10.1109\/IISA66859.2025.11311216"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658948"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSDE59766.2023.10487759"},{"key":"e_1_3_2_1_45_1","unstructured":"Pantid Chantangphol Pornchanan Balee Kantapong Sucharitpongpan Chanatip Saetia and Tawunrat Chalothorn. 2025. FinMind-Y-Me at the Regulations Challenge Task: Financial Mind Your Meaning based on THaLLE. In Proceedings of the Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP) the 6th Financial Narrative Processing (FNP) and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal) Chung-Chi Chen Antonio Moreno-Sandoval Jimin Huang Qianqian Xie Sophia Ananiadou and Hsin-Hsi Chen (Eds.). Association for Computational Linguistics Abu Dhabi UAE 349\u2013362. https:\/\/aclanthology.org\/2025.finnlp-1.41\/"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1745"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3772318.3791428"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.00231"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","unstructured":"Bocheng Chen Hanqing Guo and Qiben Yan. 2024. FlexLLM: Exploring LLM Customization for Moving Target Defense on Black-Box LLMs Against Jailbreak Attacks. doi:10.48550\/arXiv.2412.07672","DOI":"10.48550\/arXiv.2412.07672"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3634737.3656289"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.529"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.14452"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72344-5_16"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.14461"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.71265\/0p137y60"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.146"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","unstructured":"Jeffrey Yang Fan Chiang Seungjae Lee Jia-Bin Huang Furong Huang and Yizheng Chen. 2025. Why Are Web AI Agents More Vulnerable Than Standalone LLMs? A Security Analysis. doi:10.48550\/arXiv.2502.20383","DOI":"10.48550\/arXiv.2502.20383"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","unstructured":"Yu Ying Chiu Liwei Jiang and Yejin Choi. 2025. DailyDilemmas: Revealing Value Preferences of LLMs with Quandaries of Daily Life. doi:10.48550\/arXiv.2410.02683","DOI":"10.48550\/arXiv.2410.02683"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","unstructured":"Yumin Choi Jinheon Baek and Sung Ju Hwang. 2025. System Prompt Optimization with Meta-Learning. doi:10.48550\/arXiv.2505.09666","DOI":"10.48550\/arXiv.2505.09666"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.frl.2025.108923"},{"key":"e_1_3_2_1_61_1","unstructured":"Chrome. 2025. The Prompt API | AI on Chrome | Chrome for Developers \u2014 developer.chrome.com. https:\/\/developer.chrome.com\/docs\/ai\/prompt-api [Accessed 13-01-2026]."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.12946"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.3390\/info12070275"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1080\/17439760.2016.1262613"},{"key":"e_1_3_2_1_65_1","unstructured":"Claude. 2025. System Prompts \u2014 platform.claude.com. https:\/\/platform.claude.com\/docs\/en\/release-notes\/system-prompts [Accessed 07-01-2026]."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445921"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594073"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1503"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.13207"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1145\/3734524"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533150"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","unstructured":"Rimom Costa. 2025. Instruction-Level Weight Shaping: A Framework for Self-Improving AI Agents. doi:10.48550\/arXiv.2509.00251","DOI":"10.48550\/arXiv.2509.00251"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","unstructured":"Yuhao Dan Zhikai Lei Yiyang Gu Yong Li Jianghao Yin Jiaju Lin Linhao Ye Zhiyan Tie Yougen Zhou Yilei Wang Aimin Zhou Ze Zhou Qin Chen Jie Zhou Liang He and Xipeng Qiu. 2023. EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education. doi:10.48550\/arXiv.2308.02773","DOI":"10.48550\/arXiv.2308.02773"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.14490"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","unstructured":"Badhan Chandra Das M. Hadi Amini and Yanzhao Wu. 2025. System Prompt Extraction Attacks and Defenses in Large Language Models. doi:10.48550\/arXiv.2505.23817","DOI":"10.48550\/arXiv.2505.23817"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1177\/2755323X241237619"},{"key":"e_1_3_2_1_77_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732122"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1164"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658990"},{"key":"e_1_3_2_1_80_1","unstructured":"DeepMind. 2025. Model cards \u2014 deepmind.google. https:\/\/deepmind.google\/models\/model-cards\/ [Accessed 11-01-2026]."},{"key":"e_1_3_2_1_81_1","unstructured":"UK Government Department for Science Innovation & Technology. 2025. Code of Practice for the Cyber Security of AI. https:\/\/www.gov.uk\/government\/publications\/ai-cyber-security-code-of-practice"},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658958"},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.557"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3659001"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","unstructured":"Joachim Diederich. 2025. Rule Encoding and Compliance in Large Language Models: An Information-Theoretic Analysis. doi:10.48550\/arXiv.2510.05106","DOI":"10.48550\/arXiv.2510.05106"},{"key":"e_1_3_2_1_86_1","unstructured":"Digital Scholar. 2025. Zotero. https:\/\/www.zotero.org\/"},{"key":"e_1_3_2_1_87_1","unstructured":"Australian Government Digital Transformation Agency. 2025. Digital Transformation Agency Annual Report 2024\u201325."},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.05903"},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658939"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","unstructured":"Guanting Dong Xiaoshuai Song Yutao Zhu Runqi Qiao Zhicheng Dou and Ji-Rong Wen. 2024. Toward General Instruction-Following Alignment for Retrieval-Augmented Generation. doi:10.48550\/arXiv.2410.09584","DOI":"10.48550\/arXiv.2410.09584"},{"key":"e_1_3_2_1_91_1","doi-asserted-by":"publisher","unstructured":"Alexander Doudkin Anton Voelker and Friedrich von Borries. 2025. The Spark Effect: On Engineering Creative Diversity in Multi-Agent AI Systems. doi:10.48550\/arXiv.2510.15568","DOI":"10.48550\/arXiv.2510.15568"},{"key":"e_1_3_2_1_92_1","doi-asserted-by":"publisher","unstructured":"Guoliang Duan Mingwei Liu Yanlin Wang Chong Wang Xin Peng and Zibin Zheng. 2025. A Hierarchical and Evolvable Benchmark for Fine-Grained Code Instruction Following with Multi-Turn Feedback. doi:10.48550\/arXiv.2507.00699","DOI":"10.48550\/arXiv.2507.00699"},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.wnu-1.2"},{"key":"e_1_3_2_1_94_1","unstructured":"European Parliament. 2024. Regulation (EU) 2024\/1689 of the European Parliament and of the Council of 13 June 2024 laying down harmonised rules on artificial intelligence and amending Regulations (EC) No 300\/2008 (EU) No 167\/2013 (EU) No 168\/2013 (EU) 2018\/858 (EU) 2018\/1139 and (EU) 2019\/2144 and Directives 2014\/90\/EU (EU) 2016\/797 and (EU) 2020\/1828 (Artificial Intelligence Act). OJ L 2024\/1289."},{"key":"e_1_3_2_1_95_1","unstructured":"Government of the USA Executive Office of the President. 2025. Executive Order 14319 Preventing Woke AI in the Federal Government. https:\/\/www.federalregister.gov\/documents\/2025\/07\/28\/2025- 14217\/preventing-woke-ai-in-the-federal-government 90 FR 35389."},{"key":"e_1_3_2_1_96_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCKE65377.2024.10874775"},{"key":"e_1_3_2_1_97_1","first-page":"3664","volume-title":"CEUR workshop proceedings 4038","author":"Farid Humaira","year":"2025","unstructured":"Humaira Farid, Zainab Ahmad, Ahmad Mahmood, and Iqra Ameer. 2025. HF Detox at TextDetox CLEF 2025: Prompt-Driven Multilingual Detoxification. CEUR workshop proceedings 4038 (2025), 3664 - 3671."},{"key":"e_1_3_2_1_98_1","unstructured":"Patrick Farley. 2025. Prompt Shields in Azure AI Content Safety - Azure AI services \u2014 learn.microsoft.com. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/content-safety\/concepts\/jailbreak-detection [Accessed 11-01-2026]."},{"key":"e_1_3_2_1_99_1","unstructured":"Patrick Farley. 2025. Protected material detection in Azure AI Content Safety - Azure AI services \u2014 learn.microsoft.com. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/content-safety\/concepts\/protected-material?tabs=text [Accessed 11-01-2026]."},{"key":"e_1_3_2_1_100_1","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_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.32738\/JEPPM-2024-0035"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"publisher","unstructured":"Michal Furmakiewicz Chang Liu Angus Taylor and Ilya Venger. 2024. Design and evaluation of AI copilots - case studies of retail copilot templates. doi:10.48550\/arXiv.2407.09512","DOI":"10.48550\/arXiv.2407.09512"},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","unstructured":"Valerii Gakh and Hayretdin Bahsi. 2025. Enhancing Security in LLM Applications: A Performance Evaluation of Early Detection Systems. doi:10.48550\/arXiv.2506.19109","DOI":"10.48550\/arXiv.2506.19109"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","unstructured":"Victor Gallego. 2024. Configurable Safety Tuning of Language Models with Synthetic Preference Data. doi:10.48550\/arXiv.2404.00495","DOI":"10.48550\/arXiv.2404.00495"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","unstructured":"V\u00edctor Gallego. 2025. MetaSC: Test-Time Safety Specification Optimization for Language Models. doi:10.48550\/arXiv.2502.07985","DOI":"10.48550\/arXiv.2502.07985"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1109\/CoG64752.2025.11114120"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","unstructured":"Peizhong Gao Ao Xie Shaoguang Mao Wenshan Wu Yan Xia Haipeng Mi and Furu Wei. 2024. Meta Reasoning for Large Language Models. doi:10.48550\/arXiv.2406.11698","DOI":"10.48550\/arXiv.2406.11698"},{"key":"e_1_3_2_1_108_1","unstructured":"Amelia Gentleman Helena Horton and Dan Milmo. 2026. Grok AI still being used to digitally undress women and children despite suspension pledge \u2014 theguardian.com. https:\/\/www.theguardian.com\/technology\/2026\/jan\/05\/elon-musk-grok-ai-digitally-undress-images-of-women-children [Accessed 10-01-2026]."},{"key":"e_1_3_2_1_109_1","unstructured":"KeremGoksel and Mona Wang. 2025. AI Alignment Is Censorship \u2014joinreboot.org. https:\/\/joinreboot.org\/p\/ai-alignment-is-censorship [Accessed 10-01-2026]."},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1080\/17579961.2024.2388914"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"publisher","unstructured":"Diego Gosmar Deborah A. Dahl and Dario Gosmar. 2025. Prompt Injection Detection and Mitigation via AI Multi-Agent NLP Frameworks. doi:10.48550\/arXiv.2503.11517","DOI":"10.48550\/arXiv.2503.11517"},{"key":"e_1_3_2_1_112_1","unstructured":"UK Government Government Digital Service. 2025. Code of Practice for the Cyber Security of AI. https:\/\/www.gov.uk\/government\/publications\/data-ethics-framework\/data-and-ai-ethics-framework"},{"key":"e_1_3_2_1_113_1","unstructured":"UK Government Government Digital Service. 2025. Artificial Intelligence Playbook for the UK Government. https:\/\/www.gov.uk\/government\/publications\/ai-playbook-for-the-uk-government\/artificial-intelligence-playbook-for-the-uk-government-html"},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","unstructured":"Ryan Greenblatt Carson Denison Benjamin Wright Fabien Roger Monte MacDiarmid Sam Marks Johannes Treutlein Tim Belonax Jack Chen David Duvenaud Akbir Khan Julian Michael S\u00f6ren Mindermann Ethan Perez Linda Petrini Jonathan Uesato Jared Kaplan Buck Shlegeris Samuel R. Bowman and Evan Hubinger. 2024. Alignment faking in large language models. doi:10.48550\/arXiv.2412.14093","DOI":"10.48550\/arXiv.2412.14093"},{"key":"e_1_3_2_1_115_1","volume-title":"GitHub - xai-org\/grok-prompts: Prompts for our Grok chat assistant and the \u2018@grok","year":"2026","unstructured":"Grok. 2025. GitHub - xai-org\/grok-prompts: Prompts for our Grok chat assistant and the \u2018@grok\u2019 bot on X. \u2014 github.com. https:\/\/github.com\/xai-org\/grok-prompts [Accessed 07-01-2026]."},{"key":"e_1_3_2_1_116_1","volume-title":"Sicheng Zhu, Christopher A. Choquette-Choo, Steph Lin, Nikhil Kandpal, Milad Nasr, Rai, Sam Toyer, Miles Wang, Yaodong Yu, Alex Beutel, and Kai Xiao.","author":"Guo Chuan","year":"2026","unstructured":"Chuan Guo, Juan Felipe Ceron Uribe, Sicheng Zhu, Christopher A. Choquette-Choo, Steph Lin, Nikhil Kandpal, Milad Nasr, Rai, Sam Toyer, Miles Wang, Yaodong Yu, Alex Beutel, and Kai Xiao. 2026. IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs. arXiv:2603.10521 [cs.AI] https:\/\/arxiv.org\/abs\/2603.10521"},{"key":"e_1_3_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.1145\/3724504.3724574"},{"key":"e_1_3_2_1_118_1","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. arXiv:2311.04892 [cs.CL] https:\/\/arxiv.org\/abs\/2311.04892"},{"key":"e_1_3_2_1_119_1","doi-asserted-by":"publisher","unstructured":"Stefan Hackmann Haniyeh Mahmoudian Mark Steadman and Michael Schmidt. 2024. Word Importance Explains How Prompts Affect Language Model Outputs. doi:10.48550\/arXiv.2403.03028","DOI":"10.48550\/arXiv.2403.03028"},{"key":"e_1_3_2_1_120_1","doi-asserted-by":"publisher","unstructured":"Thilo Hagendorff Erik Derner and Nuria Oliver. 2025. Large Reasoning Models Are Autonomous Jailbreak Agents. doi:10.48550\/arXiv.2508.04039","DOI":"10.48550\/arXiv.2508.04039"},{"key":"e_1_3_2_1_121_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3717814"},{"key":"e_1_3_2_1_122_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1295"},{"key":"e_1_3_2_1_123_1","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-5084169\/v1"},{"key":"e_1_3_2_1_124_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.896"},{"key":"e_1_3_2_1_125_1","doi-asserted-by":"publisher","unstructured":"Hassan Harb Yunkai Sun Mustafa Unal Abhishek Aggarwal Chiara Bissolotti I\u015fiksu B\u00fcy\u00fcker Sungil Hong Luke Johnson Lateef Jolaoso Bratin Sengupta Michael Stuhr Zhenzhen Yang Brian Ingram and Rajeev Surendran Assary. 2025. Towards Philosophical Reasoning with Agentic LLMs: Socratic Method for Scientific Assistance. doi:10.26434\/chemrxiv-2025-rwxdk","DOI":"10.26434\/chemrxiv-2025-rwxdk"},{"key":"e_1_3_2_1_126_1","doi-asserted-by":"publisher","unstructured":"Itay Hazan Idan Habler Ron Bitton and Itsik Mantin. 2025. Security Steerability is All You Need. doi:10.48550\/arXiv.2504.19521","DOI":"10.48550\/arXiv.2504.19521"},{"key":"e_1_3_2_1_127_1","doi-asserted-by":"publisher","unstructured":"Jiajie He Yuechun Gu Min-Chun Chen and Keke Chen. 2025. Membership Inference Attacks on LLM-based Recommender Systems. doi:10.48550\/arXiv.2508.18665","DOI":"10.48550\/arXiv.2508.18665"},{"key":"e_1_3_2_1_128_1","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.2025.2487310"},{"key":"e_1_3_2_1_129_1","doi-asserted-by":"publisher","unstructured":"Bernd Hofmann Sven Kreitlein Joerg Franke and Patrick Bruendl. 2025. Beyond touch-based HMI: Control your machines in natural language by utilizing large language models and OPC UA. doi:10.48550\/arXiv.2510.11300","DOI":"10.48550\/arXiv.2510.11300"},{"key":"e_1_3_2_1_130_1","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v8i2.36628"},{"key":"e_1_3_2_1_131_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732017"},{"key":"e_1_3_2_1_132_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732017"},{"key":"e_1_3_2_1_133_1","unstructured":"https:\/\/www.nytimes.com\/by\/dylan freedman. [n.d.]. The Day ChatGPT Went Cold \u2014 nytimes.com. https:\/\/www.nytimes.com\/2025\/08\/19\/business\/chatgpt-gpt-5-backlash-openai.html [Accessed 07-09-2025]."},{"key":"e_1_3_2_1_134_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.09125"},{"key":"e_1_3_2_1_135_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.504"},{"key":"e_1_3_2_1_136_1","unstructured":"HuggingFace. 2025. https:\/\/huggingface.co\/blog\/codelion\/system-prompt-learning [Accessed 07-09-2025]."},{"key":"e_1_3_2_1_137_1","unstructured":"HuggingFace. 2025. Model Cards \u2014 huggingface.co. https:\/\/huggingface.co\/docs\/hub\/en\/model-cards [Accessed 11-01-2026]."},{"key":"e_1_3_2_1_138_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3670370"},{"key":"e_1_3_2_1_139_1","doi-asserted-by":"publisher","DOI":"10.1145\/3768292.3770385"},{"key":"e_1_3_2_1_140_1","unstructured":"Government of Singapore IMDA. 2025. Starter Kit for Safety Testingof LLM-Based Applications Draft for Public Consultation. https:\/\/www.imda.gov.sg\/-\/media\/imda\/files\/about\/emerging-tech-and-research\/artificial-intelligence\/large-language-model-starter-kit.pdf"},{"key":"e_1_3_2_1_141_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.1302"},{"key":"e_1_3_2_1_142_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics14183624"},{"key":"e_1_3_2_1_143_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533097"},{"key":"e_1_3_2_1_144_1","volume-title":"Can AI Really \u2018Interpret","author":"Jane\u010dek V\u00e1clav","year":"2025","unstructured":"V\u00e1clav Jane\u010dek. 2025. Can AI Really \u2018Interpret\u2019 the Law? Rethinking Large Language Models as Probabilistic Evaluators, Not Robot Judges. https:\/\/legalresearch.blogs.bris.ac.uk\/2025\/12\/can-ai-really-interpret-the-law-rethinking-large-language-models-as-probabilistic-evaluators-not-robot-judges\/ [Accessed 13-01-2026]."},{"key":"e_1_3_2_1_145_1","doi-asserted-by":"publisher","unstructured":"Daniel Jaroslawicz Brendan Whiting Parth Shah and Karime Maamari. 2025. How Many Instructions Can LLMs Follow at Once? doi:10.48550\/arXiv.2507.11538","DOI":"10.48550\/arXiv.2507.11538"},{"key":"e_1_3_2_1_146_1","unstructured":"Colin Jarvis. 2023. How to implement LLM guardrails | OpenAI Cookbook \u2014 cookbook.openai.com. https:\/\/cookbook.openai.com\/examples\/how_to_use_guardrails [Accessed 11-01-2026]."},{"key":"e_1_3_2_1_147_1","doi-asserted-by":"publisher","unstructured":"Minbyul Jeong Jungho Cho Minsoo Khang Dawoon Jung and Teakgyu Hong. 2025. System Message Generation for User Preferences using Open-Source Models. doi:10.48550\/arXiv.2502.11330","DOI":"10.48550\/arXiv.2502.11330"},{"key":"e_1_3_2_1_148_1","doi-asserted-by":"publisher","unstructured":"Qi Jia Kaiwei Zhang Xiujie Song Ye Shen Xiangyang Zhu and Guangtao Zhai. 2025. One Battle After Another: Probing LLMs' Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework. doi:10.48550\/arXiv.2511.03508","DOI":"10.48550\/arXiv.2511.03508"},{"key":"e_1_3_2_1_149_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.147"},{"key":"e_1_3_2_1_150_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732049"},{"key":"e_1_3_2_1_151_1","doi-asserted-by":"publisher","unstructured":"Erik Jones Hamid Palangi Clarisse Sim\u00f5es Varun Chandrasekaran Subhabrata Mukherjee Arindam Mitra Ahmed Awadallah and Ece Kamar. 2023. Teaching Language Models to Hallucinate Less with Synthetic Tasks. doi:10.48550\/arXiv.2310.06827","DOI":"10.48550\/arXiv.2310.06827"},{"key":"e_1_3_2_1_152_1","doi-asserted-by":"publisher","DOI":"10.1093\/polsoc\/puae020"},{"key":"e_1_3_2_1_153_1","unstructured":"kagent. 2025. How to write system prompts \u2014 kagent.dev. https:\/\/kagent.dev\/docs\/kagent\/getting-started\/system-prompts [Accessed 11-01-2026]."},{"key":"e_1_3_2_1_154_1","doi-asserted-by":"publisher","DOI":"10.5435\/JAAOS-D-25-00456"},{"key":"e_1_3_2_1_155_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.14539"},{"key":"e_1_3_2_1_156_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2511.00230"},{"key":"e_1_3_2_1_157_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.947"},{"key":"e_1_3_2_1_158_1","doi-asserted-by":"publisher","unstructured":"Christian Kempny K\u00fcbra Annac Yuece Yilmaz-Aslan and Patrick Brzoska. 2025. QualiPilot - an of fline AI tool for qualitative content analysis. doi:10.21203\/rs.3.rs-7122121\/v1","DOI":"10.21203\/rs.3.rs-7122121\/v1"},{"key":"e_1_3_2_1_159_1","doi-asserted-by":"publisher","unstructured":"Gauri Kholkar and Ratinder Ahuja. 2025. Policy-as-Prompt: Turning AI Governance Rules into Guardrails for AI Agents. doi:10.48550\/arXiv.2509.23994","DOI":"10.48550\/arXiv.2509.23994"},{"key":"e_1_3_2_1_160_1","doi-asserted-by":"publisher","unstructured":"Shaun Khoo Gabriel Chua and Rachel Shong. 2025. MinorBench: A hand-built benchmark for content-based risks for children. doi:10.48550\/arXiv.2503.10242","DOI":"10.48550\/arXiv.2503.10242"},{"key":"e_1_3_2_1_161_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1034"},{"key":"e_1_3_2_1_162_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.09038"},{"key":"e_1_3_2_1_163_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658543"},{"key":"e_1_3_2_1_164_1","unstructured":"Will Knight. [n. d.]. OpenAI Scrambles to Update GPT-5 After Users Revolt \u2014 wired.com. https:\/\/www.wired.com\/story\/openai-gpt-5-backlash-sam-altman\/ [Accessed 07-09-2025]."},{"key":"e_1_3_2_1_165_1","doi-asserted-by":"publisher","DOI":"10.1080\/17579961.2021.1898299"},{"key":"e_1_3_2_1_166_1","doi-asserted-by":"crossref","unstructured":"Anton Korinek and Avital Balwit. 2022. Aligned with Whom? Direct and social goals for AI systems. arXiv:2205.04279 [cs.CY] https:\/\/arxiv.org\/abs\/2205.04279","DOI":"10.3386\/w30017"},{"key":"e_1_3_2_1_167_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.17938"},{"key":"e_1_3_2_1_168_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-54827-7_2"},{"key":"e_1_3_2_1_169_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732191"},{"key":"e_1_3_2_1_170_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.00441"},{"key":"e_1_3_2_1_171_1","doi-asserted-by":"publisher","unstructured":"Sai Adith Senthil Kumar Hao Yan Saipavan Perepa Murong Yue and Ziyu Yao. 2025. Can LLMs Simulate Personas with Reversed Performance? A Benchmark for Counterfactual Instruction Following. doi:10.48550\/arXiv.2504.06460","DOI":"10.48550\/arXiv.2504.06460"},{"key":"e_1_3_2_1_172_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.140"},{"key":"e_1_3_2_1_173_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.7"},{"key":"e_1_3_2_1_174_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIFEr62890.2024.10772804"},{"key":"e_1_3_2_1_175_1","doi-asserted-by":"publisher","DOI":"10.1002\/cbic.202500678"},{"key":"e_1_3_2_1_176_1","doi-asserted-by":"publisher","unstructured":"Justin S Lee and Ghang Lee. 2025. A Large Language Model as an Assistant for Software- Independent Structural Analytical Model Review and Editing. (2025). doi:10.22260\/ISARC2025\/0009","DOI":"10.22260\/ISARC2025\/0009"},{"key":"e_1_3_2_1_177_1","doi-asserted-by":"publisher","unstructured":"Minjae Lee and Minsuk Kahng. 2025. Data-Model Co-Evolution: Growing Test Sets to Refine LLM Behavior. doi:10.48550\/arXiv.2510.12728","DOI":"10.48550\/arXiv.2510.12728"},{"key":"e_1_3_2_1_178_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2347"},{"key":"e_1_3_2_1_179_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.26495"},{"key":"e_1_3_2_1_180_1","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v7i1.31684"},{"key":"e_1_3_2_1_181_1","doi-asserted-by":"publisher","unstructured":"Roman Levin Valeriia Cherepanova Abhimanyu Hans Avi Schwarzschild and Tom Goldstein. 2025. Has My System Prompt Been Used? Large Language Model Prompt Membership Inference. doi:10.48550\/arXiv.2502.09974","DOI":"10.48550\/arXiv.2502.09974"},{"key":"e_1_3_2_1_182_1","unstructured":"Gideon Lewis-Kraus. 2026. Claude A.I. Versus the Pentagon \u2014 newyorker.com. https:\/\/www.newyorker.com\/news\/annals-of-inquiry\/the-pentagon-went-to-war-with-anthropic-whats-really-at-stake [Accessed 17-03-2026]."},{"key":"e_1_3_2_1_183_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.20749"},{"key":"e_1_3_2_1_184_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.24418"},{"key":"e_1_3_2_1_185_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.ijcnlp-long.116"},{"key":"e_1_3_2_1_186_1","doi-asserted-by":"publisher","unstructured":"Kenneth Li Tianle Liu Naomi Bashkansky David Bau Fernanda Vi\u00e9gas Hanspeter Pfister and Martin Wattenberg. 2024. Measuring and Controlling Instruction (In)Stability in Language Model Dialogs. doi:10.48550\/arXiv.2402.10962","DOI":"10.48550\/arXiv.2402.10962"},{"key":"e_1_3_2_1_187_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.13281"},{"key":"e_1_3_2_1_188_1","doi-asserted-by":"publisher","unstructured":"Xiaomin Li Zhou Yu Zhiwei Zhang Xupeng Chen Ziji Zhang Yingying Zhuang Narayanan Sadagopan and Anurag Beniwal. 2025. When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs. doi:10.48550\/arXiv.2505.11423","DOI":"10.48550\/arXiv.2505.11423"},{"key":"e_1_3_2_1_189_1","doi-asserted-by":"publisher","unstructured":"Yucheng Li Surin Ahn Huiqiang Jiang Amir H. Abdi Yuqing Yang and Lili Qiu. 2025. SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression. doi:10.48550\/arXiv.2506.12707","DOI":"10.48550\/arXiv.2506.12707"},{"key":"e_1_3_2_1_190_1","doi-asserted-by":"publisher","unstructured":"Yafu Li Xuyang Hu Xiaoye Qu Linjie Li and Yu Cheng. 2025. Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback. doi:10.48550\/arXiv.2501.12895","DOI":"10.48550\/arXiv.2501.12895"},{"key":"e_1_3_2_1_191_1","doi-asserted-by":"publisher","unstructured":"Yiming Li Shuo Shao Yu He Junfeng Guo Tianwei Zhang Zhan Qin Pin-Yu Chen Michael Backes Philip Torr Dacheng Tao and Kui Ren. 2025. Rethinking Data Protection in the (Generative) Artificial Intelligence Era. doi:10.48550\/arXiv.2507.03034","DOI":"10.48550\/arXiv.2507.03034"},{"key":"e_1_3_2_1_192_1","doi-asserted-by":"publisher","unstructured":"Zongze Li Jiawei Guo and Haipeng Cai. 2025. System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection. doi:10.48550\/arXiv.2505.06493","DOI":"10.48550\/arXiv.2505.06493"},{"key":"e_1_3_2_1_193_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i38.40457"},{"key":"e_1_3_2_1_194_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.33"},{"key":"e_1_3_2_1_195_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI61247.2024.00059"},{"key":"e_1_3_2_1_196_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.05223"},{"key":"e_1_3_2_1_197_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.09754"},{"key":"e_1_3_2_1_198_1","doi-asserted-by":"publisher","unstructured":"Jiashuo Liang Guancheng Li and Yang Yu. 2024. Universal and Context-Independent Triggers for Precise Control of LLM Outputs. doi:10.48550\/arXiv.2411.14738","DOI":"10.48550\/arXiv.2411.14738"},{"key":"e_1_3_2_1_199_1","doi-asserted-by":"publisher","unstructured":"Ilija Lichkovski Alexander M\u00fcller Mariam Ibrahim and Tiwai Mhundwa. 2025. EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law. doi:10.48550\/arXiv.2510.21524","DOI":"10.48550\/arXiv.2510.21524"},{"key":"e_1_3_2_1_200_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3593992"},{"key":"e_1_3_2_1_201_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580953"},{"key":"e_1_3_2_1_202_1","doi-asserted-by":"publisher","unstructured":"Bill Yuchen Lin Abhilasha Ravichander Ximing Lu Nouha Dziri Melanie Sclar Khyathi Chandu Chandra Bhagavatula and Yejin Choi. 2023. The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning. doi:10.48550\/arXiv.2312.01552","DOI":"10.48550\/arXiv.2312.01552"},{"key":"e_1_3_2_1_203_1","doi-asserted-by":"publisher","unstructured":"Andy Liu Kshitish Ghate Mona Diab Daniel Fried Atoosa Kasirzadeh and Max Kleiman-Weiner. 2025. Generative Value Conflicts Reveal LLM Priorities. doi:10.48550\/arXiv.2509.25369","DOI":"10.48550\/arXiv.2509.25369"},{"key":"e_1_3_2_1_204_1","doi-asserted-by":"publisher","unstructured":"Jiateng Liu Zhenhailong Wang Xiaojiang Huang Yingjie Li Xing Fan Xiang Li Chenlei Guo Ruhi Sarikaya and Heng Ji. 2025. Analyzing and Internalizing Complex Policy Documents for LLM Agents. doi:10.48550\/arXiv.2510.11588","DOI":"10.48550\/arXiv.2510.11588"},{"key":"e_1_3_2_1_205_1","volume-title":"Syed Fahad Allam Shah, Sujith Ravi, and Dan Roth.","author":"Liu Marianne Menglin","year":"2026","unstructured":"Marianne Menglin Liu, Sai Ashish Somayajula, Syed Fahad Allam Shah, Sujith Ravi, and Dan Roth. 2026. OraPlan-SQL: A Planning-Centric Framework for Complex Bilingual NL2SQL Reasoning. In Knowledge Graphs, Hideaki Takeda, Yannis Tzitzikas, Giorgos Flouris, Shizhu He, Dimitris Plexousakis, S\u00e9bastien Ferr\u00e9, Ran Yu, Vasilis Efthymiou, Eleni Ilkou, Ernesto Jim\u00e9nez-Ruiz, and Xin Wang (Eds.). Springer Nature Singapore, Singapore, 537\u2013544."},{"key":"e_1_3_2_1_206_1","volume-title":"Proceedings of the International Conference on Neuro-symbolic Systems (Proceedings of Machine Learning Research","volume":"764","author":"Liu Tian Yu","year":"2025","unstructured":"Tian Yu Liu, Stefano Soatto, Matteo Marchi, Pratik Chaudhari, and Paulo Tabuada. 2025. Observability of Latent States in Generative AI Models. In Proceedings of the International Conference on Neuro-symbolic Systems (Proceedings of Machine Learning Research, Vol. 288), George Pappas, Pradeep Ravikumar, and Sanjit A. Seshia (Eds.). PMLR, 745\u2013764. https:\/\/proceedings.mlr.press\/v288\/liu25b.html"},{"key":"e_1_3_2_1_207_1","volume-title":"Notebook for the PAN Lab at CLEF","author":"Liu Xiaohui","year":"2025","unstructured":"Xiaohui Liu, Yusheng Yi, Zhaotian Chen, Simin Xu, Zijun Ke, Xin Guo, Yubo Huang, Wenxuan Zhang, Jiayi Chen, and Yong Han. 2025. Notebook for the PAN Lab at CLEF 2025. (2025)."},{"key":"e_1_3_2_1_208_1","doi-asserted-by":"publisher","unstructured":"Yupei Liu Yanting Wang Yuqi Jia Jinyuan Jia and Neil Zhenqiang Gong. 2025. SecInfer: Preventing Prompt Injection via Inference-time Scaling. doi:10.48550\/arXiv.2509.24967","DOI":"10.48550\/arXiv.2509.24967"},{"key":"e_1_3_2_1_209_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1082"},{"key":"e_1_3_2_1_210_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-9994-0_43"},{"key":"e_1_3_2_1_211_1","doi-asserted-by":"publisher","unstructured":"Lucy Macnaught. 2025. Designing AI agents for writing development: Anticipating semiotic mediation with the theoretical architecture of Systemic Functional Linguistics. doi:10.2139\/ssrn.5558287","DOI":"10.2139\/ssrn.5558287"},{"key":"e_1_3_2_1_212_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642861"},{"key":"e_1_3_2_1_213_1","doi-asserted-by":"publisher","unstructured":"Sharan Maiya Henning Bartsch Nathan Lambert and Evan Hubinger. 2025. Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI. doi:10.48550\/arXiv.2511.01689","DOI":"10.48550\/arXiv.2511.01689"},{"key":"e_1_3_2_1_214_1","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.13571"},{"key":"e_1_3_2_1_215_1","doi-asserted-by":"publisher","unstructured":"Narek Maloyan and Dmitry Namiot. 2025. Adversarial Attacks on LLM-as-a-Judge Systems: Insights from Prompt Injections. doi:10.48550\/arXiv.2504.18333","DOI":"10.48550\/arXiv.2504.18333"},{"key":"e_1_3_2_1_216_1","doi-asserted-by":"publisher","unstructured":"Ingo Marquardt and Philippe Brule. 2025. Fine-tuning on simulated data outperforms prompting for agent tone of voice. doi:10.48550\/arXiv.2507.04889","DOI":"10.48550\/arXiv.2507.04889"},{"key":"e_1_3_2_1_217_1","doi-asserted-by":"publisher","DOI":"10.1002\/pra2.1473"},{"key":"e_1_3_2_1_218_1","doi-asserted-by":"publisher","unstructured":"Lachlan McGinness and Peter Baumgartner. 2025. Large Language Models' Reasoning Stalls: An Investigation into the Capabilities of Frontier Models. doi:10.48550\/arXiv.2505.19676","DOI":"10.48550\/arXiv.2505.19676"},{"key":"e_1_3_2_1_219_1","doi-asserted-by":"publisher","DOI":"10.18293\/SEKE2025-022"},{"key":"e_1_3_2_1_220_1","doi-asserted-by":"publisher","unstructured":"Forough Mehralian Ryan Shar James R. Rae and Alireza Hashemi. 2025. CodeAlignBench: Assessing Code Generation Models on Developer-Preferred Code Adjustments. doi:10.48550\/arXiv.2510.27565","DOI":"10.48550\/arXiv.2510.27565"},{"key":"e_1_3_2_1_221_1","unstructured":"Microsoft. 2025. System Message | Learn how to interact with OpenAI models \u2014 microsoft.github.io. https:\/\/microsoft.github.io\/Workshop-Interact-with-OpenAI-models\/Part-2-labs\/System-Message\/ [Accessed 07-01-2026]."},{"key":"e_1_3_2_1_222_1","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"e_1_3_2_1_223_1","doi-asserted-by":"publisher","DOI":"10.7326\/ANNALS-24-03933"},{"key":"e_1_3_2_1_224_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3910"},{"key":"e_1_3_2_1_225_1","doi-asserted-by":"publisher","unstructured":"Norman Mu Sarah Chen Zifan Wang Sizhe Chen David Karamardian Lulwa Aljeraisy Basel Alomair Dan Hendrycks and David Wagner. 2024. Can LLMs Follow Simple Rules? doi:10.48550\/arXiv.2311.04235","DOI":"10.48550\/arXiv.2311.04235"},{"key":"e_1_3_2_1_226_1","doi-asserted-by":"publisher","unstructured":"Norman Mu Jonathan Lu Michael Lavery and David Wagner. 2025. A Closer Look at System Prompt Robustness. doi:10.48550\/arXiv.2502.12197","DOI":"10.48550\/arXiv.2502.12197"},{"key":"e_1_3_2_1_227_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCloud66326.2025.00059"},{"key":"e_1_3_2_1_228_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.02707"},{"key":"e_1_3_2_1_229_1","doi-asserted-by":"publisher","DOI":"10.1109\/EDUCON62633.2025.11016405"},{"key":"e_1_3_2_1_230_1","doi-asserted-by":"publisher","unstructured":"Abdullah Mushtaq Imran Taj Rafay Naeem Ibrahim Ghaznavi and Junaid Qadir. 2025. WorldView-Bench: A Benchmark for Evaluating Global Cultural Perspectives in Large Language Models. doi:10.48550\/arXiv.2505.09595","DOI":"10.48550\/arXiv.2505.09595"},{"key":"e_1_3_2_1_231_1","doi-asserted-by":"publisher","unstructured":"Hannah Sophie Muti Chiara Maria Lavinia L\u00f6ffler Marie-Elisabeth Le\u00dfmann Esther Helene St\u00fcker Johanna Kirchberg Malte von Bonin Martin Kolditz Dyke Ferber Katharina Egger-Heidrich Felix Merboth Daniel E. Stange Marius Distler and Jakob Nikolas Kather. 2024. Customizing GPT-4 for clinical information retrieval from standard operating procedures. doi:10.1101\/2024.06.24.24309221","DOI":"10.1101\/2024.06.24.24309221"},{"key":"e_1_3_2_1_232_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.04018"},{"key":"e_1_3_2_1_233_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594074"},{"key":"e_1_3_2_1_234_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.11824"},{"key":"e_1_3_2_1_235_1","doi-asserted-by":"publisher","unstructured":"Murtaza Nazir Matthew Finlayson John X. Morris Xiang Ren and Swabha Swayamdipta. 2025. Better Language Model Inversion by Compactly Representing Next-Token Distributions. doi:10.48550\/arXiv.2506.17090","DOI":"10.48550\/arXiv.2506.17090"},{"key":"e_1_3_2_1_236_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.5579570"},{"key":"e_1_3_2_1_237_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732038"},{"key":"e_1_3_2_1_238_1","doi-asserted-by":"publisher","DOI":"10.1145\/3772318.3791726"},{"key":"e_1_3_2_1_239_1","doi-asserted-by":"publisher","unstructured":"Anna Neumann and Jatinder Singh. 2026. AI Safety Evaluations Need To Consider Cascading Effects. doi:10.48550\/arXiv.2603.00088 arXiv:2603.00088 [cs].","DOI":"10.48550\/arXiv.2603.00088"},{"key":"e_1_3_2_1_240_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2511.14130"},{"key":"e_1_3_2_1_241_1","doi-asserted-by":"publisher","unstructured":"Quang-Dung Nguyen Tri-Dung Tran Thanh-Hieu Chu Hoang-Loc Tran Xiangwei Cheng and Dirk Slama. 2025. Software Defined Vehicle Code Generation: A Few-Shot Prompting Approach. doi:10.48550\/arXiv.2511.04849","DOI":"10.48550\/arXiv.2511.04849"},{"key":"e_1_3_2_1_242_1","doi-asserted-by":"publisher","unstructured":"Yuzhou Nie Zhun Wang Ye Yu Xian Wu Xuandong Zhao Wenbo Guo and Dawn Song. 2025. LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage. In COLM. arXiv. doi:10.48550\/arXiv.2412.05734","DOI":"10.48550\/arXiv.2412.05734"},{"key":"e_1_3_2_1_243_1","volume-title":"Is the Next Antitrust Problem the Prompt to an AI Agent? | TechPolicy","author":"Nikhil Jain Meghana Kiran","year":"2026","unstructured":"Meghana Kiran Nikhil Jain. 2025. Is the Next Antitrust Problem the Prompt to an AI Agent? | TechPolicy.Press \u2014 techpolicy.press. https:\/\/www.techpolicy.press\/is-the-next-antitrust-problem-the-prompt-to-an-ai-agent\/ [Accessed 02-01-2026]."},{"key":"e_1_3_2_1_244_1","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"Noels Sander","unstructured":"Sander Noels, Guillaume Bied, Maarten Buyl, Alexander Rogiers, Yousra Fettach, Jefrey Lijffijt, and Tijl De Bie. 2026. What Large Language Models Do Not Talk About: An Empirical Study of Moderation and Censorship Practices. In Machine Learning and Knowledge Discovery in Databases. Research Track, Rita P. Ribeiro, Bernhard Pfahringer, Nathalie Japkowicz, Pedro Larra\u00f1aga, Al\u00edpio M. Jorge, Carlos Soares, Pedro H. Abreu, and Jo\u00e3o Gama (Eds.). Springer Nature Switzerland, Cham, 265\u2013281."},{"key":"e_1_3_2_1_245_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533133"},{"key":"e_1_3_2_1_246_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533133"},{"key":"e_1_3_2_1_247_1","doi-asserted-by":"publisher","unstructured":"Felix Ocker Daniel Tanneberg Julian Eggert and Michael Gienger. 2024. Tulip Agent - Enabling LLM-Based Agents to Solve Tasks Using Large Tool Libraries. doi:10.48550\/arXiv.2407.21778","DOI":"10.48550\/arXiv.2407.21778"},{"key":"e_1_3_2_1_248_1","doi-asserted-by":"publisher","DOI":"10.1145\/3733802.3764054"},{"key":"e_1_3_2_1_249_1","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v8i2.36686"},{"key":"e_1_3_2_1_250_1","doi-asserted-by":"publisher","DOI":"10.18820\/24150479\/aa49i1.1"},{"key":"e_1_3_2_1_251_1","unstructured":"ollama. 2025. Generate a response - Ollama \u2014 docs.ollama.com. https:\/\/docs.ollama.com\/api\/generate [Accessed 13-01-2026]."},{"key":"e_1_3_2_1_252_1","unstructured":"OpenAI. 2023. Introducing GPTs \u2014 openai.com. https:\/\/openai.com\/index\/introducing-gpts\/ [Accessed 08-09-2025]."},{"key":"e_1_3_2_1_253_1","volume-title":"Neu: AgentKit \u2014 openai.com. https:\/\/openai.com\/de-DE\/index\/introducing-agentkit\/ [Accessed 13-01-2026].","author":"AI.","year":"2025","unstructured":"OpenAI. 2025. Neu: AgentKit \u2014 openai.com. https:\/\/openai.com\/de-DE\/index\/introducing-agentkit\/ [Accessed 13-01-2026]."},{"key":"e_1_3_2_1_254_1","unstructured":"OpenAI. 2025. OpenAI Model Spec \u2014 model-spec.openai.com. https:\/\/model-spec.openai.com\/2025-12-18.html [Accessed 02-01-2026]."},{"key":"e_1_3_2_1_255_1","unstructured":"OpenAI. 2025. Prompt engineering | OpenAI API \u2014 platform.openai.com. https:\/\/platform.openai.com\/docs\/guides\/prompt-engineering [Accessed 11-01-2026]."},{"key":"e_1_3_2_1_256_1","unstructured":"OpenAI. 2026. API Platform \u2014 openai.com. https:\/\/openai.com\/api\/ [Accessed 09-01-2026]."},{"key":"e_1_3_2_1_257_1","unstructured":"OpenAI. 2026. Our agreement with the Department of War \u2014 openai.com. https:\/\/openai.com\/index\/our-agreement-with-the-department-of-war\/ [Accessed 17-03-2026]."},{"key":"e_1_3_2_1_258_1","volume-title":"Oh (Eds.)","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, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F Christiano, Jan Leike, and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., 27730\u201327744. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/b1efde53be364a73914f58805a001731-Paper-Conference.pdf"},{"key":"e_1_3_2_1_259_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.n71"},{"key":"e_1_3_2_1_260_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732054"},{"key":"e_1_3_2_1_261_1","doi-asserted-by":"publisher","unstructured":"Alexander Pan Lijie Chen and Jacob Steinhardt. 2024. LatentQA: Teaching LLMs to Decode Activations Into Natural Language. doi:10.48550\/arXiv.2412.08686","DOI":"10.48550\/arXiv.2412.08686"},{"key":"e_1_3_2_1_262_1","doi-asserted-by":"publisher","DOI":"10.1093\/pnasnexus\/pgag013"},{"key":"e_1_3_2_1_263_1","doi-asserted-by":"publisher","unstructured":"Akash Kumar Panda Olaoluwa Adigun and Bart Kosko. 2025. Causal Autoencoder-like Generation of Feedback Fuzzy Cognitive Maps with an LLM Agent. doi:10.48550\/arXiv.2509.25593","DOI":"10.48550\/arXiv.2509.25593"},{"key":"e_1_3_2_1_264_1","volume-title":"34th USENIX Security Symposium (USENIX Security 25)","author":"Pape David","year":"2025","unstructured":"David Pape, Sina Mavali, Thorsten Eisenhofer, and Lea Sch\u00f6nherr. 2025. Prompt obfuscation for large language models. In 34th USENIX Security Symposium (USENIX Security 25). 2323\u20132342."},{"key":"e_1_3_2_1_265_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.776"},{"key":"e_1_3_2_1_266_1","volume-title":"Proceedings of the 34th USENIX Conference on Security Symposium (SEC '25)","author":"Pasquini Dario","year":"2025","unstructured":"Dario Pasquini, Evgenios M. Kornaropoulos, and Giuseppe Ateniese. 2025. LLMmap: fingerprinting for large language models. In Proceedings of the 34th USENIX Conference on Security Symposium (SEC '25). USENIX Association, USA, 299\u2013318."},{"key":"e_1_3_2_1_267_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.506"},{"key":"e_1_3_2_1_268_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3032"},{"key":"e_1_3_2_1_269_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i25.34832"},{"key":"e_1_3_2_1_270_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"49194","author":"Pfister Niklas","year":"2025","unstructured":"Niklas Pfister, V\u00e1clav Volhejn, Manuel Knott, Santiago Arias, Julia Bazinska, Mykhailo Bichurin, Alan Y. Commike, Janet Darling, Peter Dienes, Matthew Fiedler, David Haber, Matthias Kraft, Marco Lancini, Max Mathys, Damian Pascual-Ortiz, Jakub Podolak, Adri\u00e0 Romero-L\u00f3pez, Kyriacos Shiarlis, Andreas Signer, Zsolt Terek, Athanasios Theocharis, Daniel Timbrell, Samuel Trautwein, Samuel Watts, Yun-Han Wu, and Mateo Rojas-Carulla. 2025. Gandalf the Red: Adaptive Security for LLMs. In Proceedings of the 42nd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 267), Aarti Singh, Maryam Fazel, Daniel Hsu, Simon Lacoste-Julien, Felix Berkenkamp, Tegan Maharaj, Kiri Wagstaff, and Jerry Zhu (Eds.). PMLR, 49150\u201349194. https:\/\/proceedings.mlr.press\/v267\/pfister25a.html"},{"key":"e_1_3_2_1_271_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.16888"},{"key":"e_1_3_2_1_272_1","doi-asserted-by":"publisher","DOI":"10.1017\/cfl.2025.9"},{"key":"e_1_3_2_1_273_1","unstructured":"Kelsey Piper. 2025. The AI that apparently wants Elon Musk to die \u2014 vox.com. https:\/\/www.vox.com\/future-perfect\/401874\/elon-musk-ai-grok-twitter-openai-chatgpt [Accessed 07-01-2026]."},{"key":"e_1_3_2_1_274_1","doi-asserted-by":"publisher","DOI":"10.5555\/3692070.3693729"},{"key":"e_1_3_2_1_275_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533201"},{"key":"e_1_3_2_1_276_1","volume-title":"Marco De Gemmis, and Giovanni Semeraro","author":"Polignano Marco","year":"2024","unstructured":"Marco Polignano, Marco De Gemmis, and Giovanni Semeraro. 2024. Unraveling the Enigma of SPLIT in Large-Language Models: The Unforeseen Impact of System Prompts on LLMs with Dissociative Identity Disorder. In Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024), Felice Dell'Orletta, Alessandro Lenci, Simonetta Montemagni, and Rachele Sprugnoli (Eds.). CEUR Workshop Proceedings, Pisa, Italy, 774\u2013780. https:\/\/aclanthology.org\/2024.clicit-1.84\/"},{"key":"e_1_3_2_1_277_1","unstructured":"PrPublica. 2025. Inside the AI Prompts DOGE Used to \u201cMunch\u201d Contracts Related to Veterans' Health \u2014 propublica.org. https:\/\/www.propublica.org\/article\/inside-ai-tool-doge-veterans-affairs-contracts-sahil-lavingia [Accessed 07-01-2026]."},{"key":"e_1_3_2_1_278_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761324"},{"key":"e_1_3_2_1_279_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.772"},{"key":"e_1_3_2_1_280_1","doi-asserted-by":"publisher","unstructured":"Yanzhao Qin Tao Zhang Tao Zhang Yanjun Shen Wenjing Luo Haoze Sun Yan Zhang Yujing Qiao Weipeng Chen Zenan Zhou Wentao Zhang and Bin Cui. 2024. SysBench: Can Large Language Models Follow System Messages? doi:10.48550\/arXiv.2408.10943","DOI":"10.48550\/arXiv.2408.10943"},{"key":"e_1_3_2_1_281_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651145"},{"key":"e_1_3_2_1_282_1","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2025.067750"},{"key":"e_1_3_2_1_283_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.753"},{"key":"e_1_3_2_1_284_1","volume-title":"Aizan Zafar, Hasan Maqbool, Ashmal Vayani, Jia Wu, and Maged Shoman.","author":"Raza Shaina","year":"2025","unstructured":"Shaina Raza, Rizwan Qureshi, Anam Zahid, Safiullah Kamawal, Ferhat Sadak, Joseph Fioresi, Muhammaed Saeed, Ranjan Sapkota, Aditya Jain, Anas Zafar, Muneeb Ul Hassan, Aizan Zafar, Hasan Maqbool, Ashmal Vayani, Jia Wu, and Maged Shoman. 2025. Who is Responsible? The Data, Models, Users or Regulations? A Comprehensive Survey on Responsible Generative AI for a Sustainable Future. arXiv:2502.08650 [cs.CY] https:\/\/arxiv.org\/abs\/2502.08650"},{"key":"e_1_3_2_1_285_1","doi-asserted-by":"publisher","unstructured":"Aashray Reddy Andrew Zagula and Nicholas Saban. 2025. AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models. doi:10.48550\/arXiv.2507.01020","DOI":"10.48550\/arXiv.2507.01020"},{"key":"e_1_3_2_1_286_1","volume-title":"\u201cmissing the mark","author":"Robertson Adi","year":"2024","unstructured":"Adi Robertson. 2024. Google apologizes for \u201cmissing the mark\u201d after Gemini generated racially diverse Nazis \u2014 theverge.com. https:\/\/www.theverge.com\/2024\/2\/21\/24079371\/google-ai-gemini-generative-inaccurate-historical [Accessed 13-01-2026]."},{"key":"e_1_3_2_1_287_1","doi-asserted-by":"publisher","unstructured":"Mikhail Rumiantsau Aliaksei Vertsel Ilya Hrytsuk and Isaiah Ballah. 2024. Beyond Fine-Tuning: Effective Strategies for Mitigating Hallucinations in Large Language Models for Data Analytics. doi:10.48550\/arXiv.2410.20024","DOI":"10.48550\/arXiv.2410.20024"},{"key":"e_1_3_2_1_288_1","doi-asserted-by":"publisher","DOI":"10.1097\/CIN.0000000000001351"},{"key":"e_1_3_2_1_289_1","volume-title":"Office of Management and Budget","author":"Vought Government","year":"2025","unstructured":"Government of the USA Russell T. Vought, Director, Office of Management and Budget. 2025. Memorandum to Heads of Executive Departments and Agencies: Increasing Public Trust in Artificial Intelligence Through Unbiased AI Principles. https:\/\/www.whitehouse.gov\/wp-content\/uploads\/2025\/12\/M- 26-04-Increasing-Public-Trust-in-Artificial-Intelligence-Through-Unbiased-AI-Principles-1.pdf"},{"key":"e_1_3_2_1_290_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.11513"},{"key":"e_1_3_2_1_291_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.01558"},{"key":"e_1_3_2_1_292_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2026.3666830"},{"key":"e_1_3_2_1_293_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.14393"},{"key":"e_1_3_2_1_294_1","unstructured":"Matthias Samwald Marta Ziosi Alexander Zacherl Yoshua Bengio Daniel Privitera Nitarshan Rajkumar Marietje Shaake Anka Reuel and Markus Anderljung. 2025. Code of Practice for General-Purpose AI Models Safety and Security Chapter. https:\/\/digital-strategy.ec.europa.eu\/en\/policies\/contents-code-gpai"},{"key":"e_1_3_2_1_295_1","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619652"},{"key":"e_1_3_2_1_296_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732015"},{"key":"e_1_3_2_1_297_1","doi-asserted-by":"publisher","unstructured":"J\u00e9r\u00e9my Scheurer Mikita Balesni and Marius Hobbhahn. 2024. Large Language Models can Strategically Deceive their Users when Put Under Pressure. doi:10.48550\/arXiv.2311.07590","DOI":"10.48550\/arXiv.2311.07590"},{"key":"e_1_3_2_1_298_1","doi-asserted-by":"publisher","unstructured":"Jeremy Schlatter Benjamin Weinstein-Raun and Jeffrey Ladish. 2025. Shutdown Resistance in Large Language Models. doi:10.48550\/arXiv.2509.14260","DOI":"10.48550\/arXiv.2509.14260"},{"key":"e_1_3_2_1_299_1","doi-asserted-by":"publisher","unstructured":"Andreas Scholl and Natalie Kiesler. 2025. Students' Feedback Requests and Interactions with the SCRIPT Chatbot: Do They Get What They Ask For? doi:10.48550\/arXiv.2507.17258","DOI":"10.48550\/arXiv.2507.17258"},{"key":"e_1_3_2_1_300_1","doi-asserted-by":"publisher","unstructured":"Dale Schuurmans Hanjun Dai and Francesco Zanini. 2024. Autoregressive Large Language Models are Computationally Universal. doi:10.48550\/arXiv.2410.03170","DOI":"10.48550\/arXiv.2410.03170"},{"key":"e_1_3_2_1_301_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.15751"},{"key":"e_1_3_2_1_302_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.11755"},{"key":"e_1_3_2_1_303_1","doi-asserted-by":"publisher","unstructured":"Erfan Shayegani Jina Suh Andy Wilson Nagu Rangan and Javier Hernandez. 2025. From Measurement to Expertise: Empathetic Expert Adapters for Context-Based Empathy in Conversational AI Agents. doi:10.48550\/arXiv.2511.03143","DOI":"10.48550\/arXiv.2511.03143"},{"key":"e_1_3_2_1_304_1","doi-asserted-by":"publisher","unstructured":"Ming Shen Raphael Shu Anurag Pratik James Gung Yubin Ge Monica Sunkara and Yi Zhang. 2025. Optimizing LLM-Based Multi-Agent System with Textual Feedback: A Case Study on Software Development. doi:10.48550\/arXiv.2505.16086","DOI":"10.48550\/arXiv.2505.16086"},{"key":"e_1_3_2_1_305_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.253"},{"key":"e_1_3_2_1_306_1","doi-asserted-by":"publisher","unstructured":"Jennifer Shi Christopher K. Frantz Christian Kimmich Saba Siddiki and Atrisha Sarkar. 2025. LLM-augmented empirical game theoretic simulation for social-ecological systems. doi:10.48550\/arXiv.2510.21965","DOI":"10.48550\/arXiv.2510.21965"},{"key":"e_1_3_2_1_307_1","doi-asserted-by":"publisher","DOI":"10.63317\/256c7ftgo8aa"},{"key":"e_1_3_2_1_308_1","doi-asserted-by":"publisher","DOI":"10.1109\/CogSIMA64436.2025.11079485"},{"key":"e_1_3_2_1_309_1","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_2_1_310_1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2018.2887201"},{"key":"e_1_3_2_1_311_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN64981.2025.11228703"},{"key":"e_1_3_2_1_312_1","doi-asserted-by":"publisher","unstructured":"Nikolai Skripko. 2025. Instruction-Following Evaluation in Function Calling for Large Language Models. doi:10.48550\/arXiv.2509.18420","DOI":"10.48550\/arXiv.2509.18420"},{"key":"e_1_3_2_1_313_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3622954"},{"key":"e_1_3_2_1_314_1","doi-asserted-by":"publisher","unstructured":"Francesco Sovrano. 2025. Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAP. doi:10.48550\/arXiv.2505.11189","DOI":"10.48550\/arXiv.2505.11189"},{"key":"e_1_3_2_1_315_1","unstructured":"Jingtong Su Jianyu Zhang Karen Ullrich L\u00e9on Bottou and Mark Ibrahim. 2025. A Single Character can Make or Break Your LLM Evals. arXiv:2510.05152 [cs.CL] https:\/\/arxiv.org\/abs\/2510.05152"},{"key":"e_1_3_2_1_316_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-95-2725-0_25"},{"key":"e_1_3_2_1_317_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-demo.24"},{"key":"e_1_3_2_1_318_1","unstructured":"tallesborges. 2025. GitHub - tallesborges\/agentic-system-prompts: A curated collection of system prompts and tool definitions from production AI coding agents \u2014 github.com. https:\/\/github.com\/tallesborges\/agentic-system-prompts [Accessed 13-01-2026]."},{"key":"e_1_3_2_1_319_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2510.04340"},{"key":"e_1_3_2_1_320_1","doi-asserted-by":"publisher","DOI":"10.1145\/3630106.3658935"},{"key":"e_1_3_2_1_321_1","doi-asserted-by":"publisher","unstructured":"Varin Thakur and Udbhav Garg. 2025. Defending against prompt injection attacks in LLMs. Makassar Indonesia. doi:10.1063\/5.0286966","DOI":"10.1063\/5.0286966"},{"key":"e_1_3_2_1_322_1","doi-asserted-by":"publisher","DOI":"10.2478\/jdis-2025-0011"},{"key":"e_1_3_2_1_323_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11192-025-05287-1"},{"key":"e_1_3_2_1_324_1","volume-title":"Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024","author":"Tuggener Don","year":"2024","unstructured":"Don Tuggener, Teresa Schneider, Ariana Huwiler, Tobias Kreienb\u00fchl, Simon Hischier, Pius von D\u00e4niken, and Susanna Niehaus. 2024. Role-Playing LLMs in Professional Communication Training: The Case of Investigative Interviews with Children. In Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024). Association for Computational Linguistics, Vienna, Austria, 249\u2013263. https:\/\/aclanthology.org\/2024.konvens-main.26\/"},{"key":"e_1_3_2_1_325_1","doi-asserted-by":"publisher","unstructured":"Kim Uittenhove Andrew Ellis Fabian Mumenthaler Ioana Gatzka and Patrick Jermann. 2025. Metacognitive Reflection in the Era of Generative AI. doi:10.21203\/rs.3.rs-6973046\/v1","DOI":"10.21203\/rs.3.rs-6973046\/v1"},{"key":"e_1_3_2_1_326_1","volume-title":"CLEF","author":"Vachharajani Poojan","year":"2025","unstructured":"Poojan Vachharajani. 2025. pjmathematician at MultiClinSUM 2025: A Novel Automated Prompt Optimization Framework for Multilingual Clinical Summarization. In Notebook for the BioASQ Lab, CLEF 2025."},{"key":"e_1_3_2_1_327_1","volume-title":"Notebook for the eRisk Lab at CLEF","author":"Vachharajani Poojan","year":"2025","unstructured":"Poojan Vachharajani. 2025. Transformer Ensembles and LLM-Powered Approaches for Depression Symptom Analysis and Contextualized Early Risk Detection. In Notebook for the eRisk Lab at CLEF 2025."},{"key":"e_1_3_2_1_328_1","volume-title":"The culture of connectivity: A critical history of social media","author":"Dijck Jos\u00e9 Van","unstructured":"Jos\u00e9 Van Dijck. 2013. The culture of connectivity: A critical history of social media. Oxford University Press."},{"key":"e_1_3_2_1_329_1","volume-title":"Nitish Shirish Keskar, and Richard Socher","author":"Varshney Lav R.","year":"2019","unstructured":"Lav R. Varshney, Nitish Shirish Keskar, and Richard Socher. 2019. Pretrained AI Models: Performativity, Mobility, and Change. arXiv:1909.03290 [cs.CY] https:\/\/arxiv.org\/abs\/1909.03290"},{"key":"e_1_3_2_1_330_1","volume-title":"\u0141 ukasz Kaiser, and Illia Polosukhin","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141 ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All you Need. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf"},{"key":"e_1_3_2_1_331_1","doi-asserted-by":"publisher","unstructured":"Aaron Verdaguer-Gonzalez Mag\u00ed Dalmau-Moreno Luis Merino and N\u00e9stor Garc\u00eda. 2025. Boosting Behavior Tree Generation for Robots with Large Language Models and Genetic Programming. In 2025 IEEE International Conference on Simulation Modeling and Programming for Autonomous Robots (SIMPAR). IEEE Palermo Italy 1\u20136. doi:10.1109\/SIMPAR62925.2025.10979061","DOI":"10.1109\/SIMPAR62925.2025.10979061"},{"key":"e_1_3_2_1_332_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.08370"},{"key":"e_1_3_2_1_333_1","doi-asserted-by":"publisher","unstructured":"Sanidhya Vijayvargiya and Rahul Lokesh. 2025. Efficient On-Device Agents via Adaptive Context Management. doi:10.48550\/arXiv.2511.03728","DOI":"10.48550\/arXiv.2511.03728"},{"key":"e_1_3_2_1_334_1","doi-asserted-by":"publisher","unstructured":"Eric Wallace Kai Xiao Reimar Leike Lilian Weng Johannes Heidecke and Alex Beutel. 2024. The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions. doi:10.48550\/arXiv.2404.13208","DOI":"10.48550\/arXiv.2404.13208"},{"key":"e_1_3_2_1_335_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715275.3732046"},{"key":"e_1_3_2_1_336_1","doi-asserted-by":"publisher","unstructured":"Jinze Wang Lu Zhang Yiyang Cui Zhishu Shen Xingjun Ma Jiong Jin and Tiehua Zhang. 2025. Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation. doi:10.48550\/arXiv.2510.08012","DOI":"10.48550\/arXiv.2510.08012"},{"key":"e_1_3_2_1_337_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.21625"},{"key":"e_1_3_2_1_338_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.13733"},{"key":"e_1_3_2_1_339_1","doi-asserted-by":"publisher","unstructured":"Liwen Wang Wenxuan Wang Shuai Wang Zongjie Li Zhenlan Ji Zongyi Lyu Daoyuan Wu and Shing-Chi Cheung. 2025. IP Leakage Attacks Targeting LLM-Based Multi-Agent Systems. doi:10.48550\/arXiv.2505.12442","DOI":"10.48550\/arXiv.2505.12442"},{"key":"e_1_3_2_1_340_1","doi-asserted-by":"publisher","unstructured":"Peiding Wang Li Zhang Fang Liu Lin Shi Minxiao Li Bo Shen and An Fu. 2025. CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation. doi:10.48550\/arXiv.2503.22688","DOI":"10.48550\/arXiv.2503.22688"},{"key":"e_1_3_2_1_341_1","doi-asserted-by":"publisher","unstructured":"Qian Wang Zhanzhi Lou Zhenheng Tang Nuo Chen Xuandong Zhao Wenxuan Zhang Dawn Song and Bingsheng He. 2025. Assessing Judging Bias in Large Reasoning Models: An Empirical Study. doi:10.48550\/arXiv.2504.09946","DOI":"10.48550\/arXiv.2504.09946"},{"key":"e_1_3_2_1_342_1","doi-asserted-by":"publisher","unstructured":"Qian Wang Zhenheng Tang Zhanzhi Lou Nuo Chen Wenxuan Wang and Bingsheng He. 2025. Towards Evaluting Fake Reasoning Bias in Language Models. doi:10.48550\/arXiv.2507.13758","DOI":"10.48550\/arXiv.2507.13758"},{"key":"e_1_3_2_1_343_1","volume-title":"Proceedings of the 42nd International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"63210","author":"Wang Zihao","year":"2025","unstructured":"Zihao Wang, Yibo Jiang, Jiahao Yu, and Heqing Huang. 2025. The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them). In Proceedings of the 42nd International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 267), Aarti Singh, Maryam Fazel, Daniel Hsu, Simon Lacoste-Julien, Felix Berkenkamp, Tegan Maharaj, Kiri Wagstaff, and Jerry Zhu (Eds.). PMLR, 63200\u201363210. https:\/\/proceedings.mlr.press\/v267\/wang25ap.html"},{"key":"e_1_3_2_1_344_1","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-S65789.2025.00037"},{"key":"e_1_3_2_1_345_1","doi-asserted-by":"publisher","unstructured":"Zhe Wang and Yanjun Qi. 2025. A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning. doi:10.48550\/arXiv.2503.12339","DOI":"10.48550\/arXiv.2503.12339"},{"key":"e_1_3_2_1_346_1","doi-asserted-by":"publisher","unstructured":"Zijun Wang Haoqin Tu Jieru Mei Bingchen Zhao Yisen Wang and Cihang Xie. 2024. AttnGCG: Enhancing Jailbreaking Attacks on LLMs with Attention Manipulation. doi:10.48550\/arXiv.2410.09040","DOI":"10.48550\/arXiv.2410.09040"},{"key":"e_1_3_2_1_347_1","doi-asserted-by":"publisher","DOI":"10.3390\/educsci15111507"},{"key":"e_1_3_2_1_348_1","doi-asserted-by":"publisher","unstructured":"Laura van Weesep Samuel Genheden Ola Engkvist and Jens Sj\u00f6lund. 2025. Exploring Modularity of Agentic Systems for Drug Discovery. doi:10.48550\/arXiv.2506.22189","DOI":"10.48550\/arXiv.2506.22189"},{"key":"e_1_3_2_1_349_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4415"},{"key":"e_1_3_2_1_350_1","doi-asserted-by":"publisher","DOI":"10.1177\/20539517231177620"},{"key":"e_1_3_2_1_351_1","unstructured":"Matteo Wong. 2025. Elon Musk Updated Grok. Guess What It Said? \u2014 theatlantic.com. https:\/\/www.theatlantic.com\/technology\/archive\/2025\/07\/new-grok-racism-elon-musk\/683515\/ [Accessed 13-01-2026]."},{"key":"e_1_3_2_1_352_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.20643"},{"key":"e_1_3_2_1_353_1","doi-asserted-by":"publisher","unstructured":"Alina Wr\u00f3blewska and Bartosz \u017duk. 2025. Integrating gender inclusivity into large language models via instruction tuning. doi:10.48550\/arXiv.2508.18466","DOI":"10.48550\/arXiv.2508.18466"},{"key":"e_1_3_2_1_354_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-99958-1_4"},{"key":"e_1_3_2_1_355_1","doi-asserted-by":"publisher","unstructured":"Sean Wu Michael Koo Fabien Scalzo and Ira Kurtz. 2025. AutoMedPrompt: A New Framework for Optimizing LLM Medical Prompts Using Textual Gradients. doi:10.48550\/arXiv.2502.15944","DOI":"10.48550\/arXiv.2502.15944"},{"key":"e_1_3_2_1_356_1","doi-asserted-by":"publisher","unstructured":"Siwei Wu Zhongyuan Peng Xinrun Du Tuney Zheng Minghao Liu Jialong Wu Jiachen Ma Yizhi Li Jian Yang Wangchunshu Zhou Qunshu Lin Junbo Zhao Zhaoxiang Zhang Wenhao Huang Ge Zhang Chenghua Lin and J. H. Liu. 2024. A Comparative Study on Reasoning Patterns of OpenAI's o1 Model. doi:10.48550\/arXiv.2410.13639","DOI":"10.48550\/arXiv.2410.13639"},{"key":"e_1_3_2_1_357_1","unstructured":"Tong Wu Shujian Zhang Kaiqiang Song Silei Xu Sanqiang Zhao Ravi Agrawal Sathish Indurthi Chong Xiang Prateek Mittal and Wenxuan Zhou. 2025. INSTRUCTIONAL SEGMENT EMBEDDING: IMPROVING LLM SAFETY WITH INSTRUCTION HIERARCHY. In 13th International Conference on Learning Representations ICLR 2025 (13th International Conference on Learning Representations ICLR 2025). International Conference on Learning Representations ICLR 78078\u201378108. Publisher Copyright: \u00a9 2025 13th International Conference on Learning Representations ICLR 2025. All rights reserved.; 13th International Conference on Learning Representations ICLR 2025 ; Conference date: 24-04-2025 Through 28-04-2025."},{"key":"e_1_3_2_1_358_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.06153"},{"key":"e_1_3_2_1_359_1","doi-asserted-by":"publisher","unstructured":"Tian Xie Zitian Gao Qingnan Ren Haoming Luo Yuqian Hong Bryan Dai Joey Zhou Kai Qiu Zhirong Wu and Chong Luo. 2025. Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning. doi:10.48550\/arXiv.2502.14768","DOI":"10.48550\/arXiv.2502.14768"},{"key":"e_1_3_2_1_360_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00765-8"},{"key":"e_1_3_2_1_361_1","doi-asserted-by":"publisher","unstructured":"Bowen Xu Shaoyu Wu Kai Liu and Lulu Hu. 2025. Mixture-of-Instructions: Aligning Large Language Models via Mixture Prompting. doi:10.48550\/arXiv.2404.18410","DOI":"10.48550\/arXiv.2404.18410"},{"key":"e_1_3_2_1_362_1","doi-asserted-by":"publisher","unstructured":"Qiantong Xu Fenglu Hong Bo Li Changran Hu Zhengyu Chen and Jian Zhang. 2023. On the Tool Manipulation Capability of Open-source Large Language Models. doi:10.48550\/arXiv.2305.16504","DOI":"10.48550\/arXiv.2305.16504"},{"key":"e_1_3_2_1_363_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-industry.20"},{"key":"e_1_3_2_1_364_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.818"},{"key":"e_1_3_2_1_365_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-industry.89"},{"key":"e_1_3_2_1_366_1","doi-asserted-by":"publisher","unstructured":"Yuchen Yang Yiming Li Hongwei Yao Enhao Huang Shuo Shao Yuyi Wang Zhibo Wang Dacheng Tao and Zhan Qin. 2025. PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs. doi:10.48550\/arXiv.2509.03117","DOI":"10.48550\/arXiv.2509.03117"},{"key":"e_1_3_2_1_367_1","doi-asserted-by":"publisher","unstructured":"Jesse Yao Saurav Acharya Priyaranjan Parida Srinivas Attipalli and Ali Dasdan. 2024. Leveraging LLMs to Enable Natural Language Search on Go-to-market Platforms. doi:10.48550\/arXiv.2411.05048","DOI":"10.48550\/arXiv.2411.05048"},{"key":"e_1_3_2_1_368_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2308.02151"},{"key":"e_1_3_2_1_369_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.623"},{"key":"e_1_3_2_1_370_1","doi-asserted-by":"publisher","unstructured":"Jiahao Yu Yuhang Wu Dong Shu Mingyu Jin Sabrina Yang and Xinyu Xing. 2024. Assessing Prompt Injection Risks in 200+ Custom GPTs. doi:10.48550\/arXiv.2311.11538","DOI":"10.48550\/arXiv.2311.11538"},{"key":"e_1_3_2_1_371_1","doi-asserted-by":"publisher","unstructured":"Manjiang Yu and Xue Li. 2024. High Order Reasoning for Time Critical Recommendation in Evidence-based Medicine. doi:10.48550\/arXiv.2405.03010","DOI":"10.48550\/arXiv.2405.03010"},{"key":"e_1_3_2_1_372_1","doi-asserted-by":"publisher","unstructured":"Zhuohao Yu Jiali Zeng Weizheng Gu Yidong Wang Jindong Wang Fandong Meng Jie Zhou Yue Zhang Shikun Zhang and Wei Ye. 2025. RewardAnything: Generalizable Principle-Following Reward Models. doi:10.48550\/arXiv.2506.03637","DOI":"10.48550\/arXiv.2506.03637"},{"key":"e_1_3_2_1_373_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34768"},{"key":"e_1_3_2_1_374_1","doi-asserted-by":"publisher","unstructured":"Ahmet Yusuf Enis Karaarslan and Omer Aydin. 2024. A RAG-based Question Answering System Proposal for Understanding Islam: MufassirQAS LLM. doi:10.36227\/techrxiv.170723304.41988020\/v1","DOI":"10.36227\/techrxiv.170723304.41988020\/v1"},{"key":"e_1_3_2_1_375_1","doi-asserted-by":"publisher","unstructured":"Siqi Zeng. 2025. Who is In Charge? Dissecting Role Conflicts in Instruction Following. doi:10.48550\/arXiv.2510.01228","DOI":"10.48550\/arXiv.2510.01228"},{"key":"e_1_3_2_1_376_1","volume-title":"ICLR 2024. All rights reserved.; 12th International Conference on Learning Representations, ICLR 2024 ; Conference date: 07-05-2024 Through 11-05-2024","author":"Zeng Zhiyuan","year":"2024","unstructured":"Zhiyuan Zeng, Jiatong Yu, Tianyu Gao, Yu Meng, Tanya Goyal, and Danqi Chen. 2024. EVALUATING LARGE LANGUAGE MODELS AT EVALUATING INSTRUCTION FOLLOWING. Publisher Copyright: \u00a9 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.; 12th International Conference on Learning Representations, ICLR 2024 ; Conference date: 07-05-2024 Through 11-05-2024."},{"key":"e_1_3_2_1_377_1","volume-title":"Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information","author":"Zhan Xiao","unstructured":"Xiao Zhan, Juan-Carlos Carrillo, William Seymour, and Jose Such. 2025. Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information. USENIX Association."},{"key":"e_1_3_2_1_378_1","doi-asserted-by":"publisher","DOI":"10.1109\/RAIIE65740.2025.11140161"},{"key":"e_1_3_2_1_379_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.819"},{"key":"e_1_3_2_1_380_1","volume-title":"13th International Conference on Learning Representations, ICLR 2025 (13th International Conference on Learning Representations, ICLR","author":"Zhang Hanrong","year":"2025","unstructured":"Hanrong Zhang, Jingyuan Huang, Kai Mei, Yifei Yao, Zhenting Wang, Chenlu Zhan, Hongwei Wang, and Yongfeng Zhang. 2025. AGENT SECURITY BENCH (ASB): FORMALIZING AND BENCHMARKING ATTACKS AND DEFENSES IN LLM-BASED AGENTS. In 13th International Conference on Learning Representations, ICLR 2025 (13th International Conference on Learning Representations, ICLR 2025). International Conference on Learning Representations, ICLR, 88011\u201388046. Publisher Copyright: \u00a9 2025 13th International Conference on Learning Representations, ICLR 2025. All rights reserved.; 13th International Conference on Learning Representations, ICLR 2025 ; Conference date: 24-04-2025 Through 28-04-2025."},{"key":"e_1_3_2_1_381_1","doi-asserted-by":"publisher","unstructured":"Jingyu Zhang Ahmed Elgohary Ahmed Magooda Daniel Khashabi and Benjamin Van Durme. 2025. Controllable Safety Alignment: Inference-Time Adaptation to Diverse Safety Requirements. doi:10.48550\/arXiv.2410.08968","DOI":"10.48550\/arXiv.2410.08968"},{"key":"e_1_3_2_1_382_1","doi-asserted-by":"publisher","unstructured":"Jiahao Zhang Zilong Wang Ruofan Wang Xingjun Ma and Yu-Gang Jiang. 2024. EnJa: Ensemble Jailbreak on Large Language Models. doi:10.48550\/arXiv.2408.03603","DOI":"10.48550\/arXiv.2408.03603"},{"key":"e_1_3_2_1_383_1","doi-asserted-by":"publisher","unstructured":"Jingxiang Zhang and Lujia Zhong. 2025. Decoding Emotion in the Deep: A Systematic Study of How LLMs Represent Retain and Express Emotion. doi:10.48550\/arXiv.2510.04064","DOI":"10.48550\/arXiv.2510.04064"},{"key":"e_1_3_2_1_384_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.14826"},{"key":"e_1_3_2_1_385_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130846"},{"key":"e_1_3_2_1_386_1","doi-asserted-by":"publisher","unstructured":"Qizheng Zhang Changran Hu Shubhangi Upasani Boyuan Ma Fenglu Hong Vamsidhar Kamanuru Jay Rainton Chen Wu Mengmeng Ji Hanchen Li Urmish Thakker James Zou and Kunle Olukotun. 2025. Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models. doi:10.48550\/arXiv.2510.04618","DOI":"10.48550\/arXiv.2510.04618"},{"key":"e_1_3_2_1_387_1","unstructured":"Shichang Zhang Hongzhe Du Jiaqi W. Ma and Himabindu Lakkaraju. 2025. Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems. arXiv:2506.00175 [cs.LG] https:\/\/arxiv.org\/abs\/2506.00175"},{"key":"e_1_3_2_1_388_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.06254"},{"key":"e_1_3_2_1_389_1","doi-asserted-by":"publisher","unstructured":"Xinghua Zhang Haiyang Yu Cheng Fu Fei Huang and Yongbin Li. 2025. IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference Optimization. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Wanxiang Che Joyce Nabende Ekaterina Shutova and Mohammad Taher Pilehvar (Eds.). Association for Computational Linguistics Vienna Austria 22185\u201322200. doi:10.18653\/v1\/2025.acl-long.1079","DOI":"10.18653\/v1\/2025.acl-long.1079"},{"key":"e_1_3_2_1_390_1","doi-asserted-by":"publisher","unstructured":"Yiming Zhang Nicholas Carlini and Daphne Ippolito. 2024. Effective Prompt Extraction from Language Models. doi:10.48550\/arXiv.2307.06865","DOI":"10.48550\/arXiv.2307.06865"},{"key":"e_1_3_2_1_391_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.findings-eacl.233"},{"key":"e_1_3_2_1_392_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.425"},{"key":"e_1_3_2_1_393_1","doi-asserted-by":"publisher","unstructured":"Zheyu Zhang Zhuorui Ye Yikang Shen and Chuang Gan. 2023. Autonomous Tree-search Ability of Large Language Models. doi:10.48550\/arXiv.2310.10686","DOI":"10.48550\/arXiv.2310.10686"},{"key":"e_1_3_2_1_394_1","doi-asserted-by":"publisher","unstructured":"Zejun Zhang Li Zhang Xin Yuan Anlan Zhang Mengwei Xu and Feng Qian. 2024. A First Look at GPT Apps: Landscape and Vulnerability. doi:10.48550\/arXiv.2402.15105","DOI":"10.48550\/arXiv.2402.15105"},{"key":"e_1_3_2_1_395_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i41.40799"},{"key":"e_1_3_2_1_396_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-5675-9_13"},{"key":"e_1_3_2_1_397_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2025.103888"},{"key":"e_1_3_2_1_398_1","doi-asserted-by":"publisher","unstructured":"Zhengyue Zhao Xiaoyun Zhang Kaidi Xu Xing Hu Rui Zhang Zidong Du Qi Guo and Yunji Chen. 2024. Adversarial Contrastive Decoding: Boosting Safety Alignment of Large Language Models via Opposite Prompt Optimization. doi:10.48550\/arXiv.2406.16743","DOI":"10.48550\/arXiv.2406.16743"},{"key":"e_1_3_2_1_399_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.888"},{"key":"e_1_3_2_1_400_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1034"},{"key":"e_1_3_2_1_401_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2511.04694"},{"key":"e_1_3_2_1_402_1","unstructured":"Han Zhou Xingchen Wan Ruoxi Sun Hamid Palangi Shariq Iqbal Ivan Vuli\u0107 Anna Korhonen and Sercan \u00d6. Arik. 2025. Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies. arXiv:2502.02533 [cs.LG] https:\/\/arxiv.org\/abs\/2502.02533"},{"key":"e_1_3_2_1_403_1","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3593972"},{"key":"e_1_3_2_1_404_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.270"},{"key":"e_1_3_2_1_405_1","doi-asserted-by":"publisher","unstructured":"Sicheng Zhu Ruiyi Zhang Bang An Gang Wu Joe Barrow Zichao Wang Furong Huang Ani Nenkova and Tong Sun. 2023. AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models. doi:10.48550\/arXiv.2310.15140","DOI":"10.48550\/arXiv.2310.15140"},{"key":"e_1_3_2_1_406_1","doi-asserted-by":"publisher","unstructured":"Zhixiong Zhuang Maria-Irina Nicolae Hui-Po Wang and Mario Fritz. 2025. ProxyPrompt: Securing System Prompts against Prompt Extraction Attacks. doi:10.48550\/arXiv.2505.11459","DOI":"10.48550\/arXiv.2505.11459"},{"key":"e_1_3_2_1_407_1","doi-asserted-by":"publisher","unstructured":"Minghui Zou Ronghui Guo Sai Zhang Xiaowang Zhang and Zhiyong Feng. 2024. BiSup: Bidirectional Quantization Error Suppression for Large Language Models. doi:10.48550\/arXiv.2405.15346","DOI":"10.48550\/arXiv.2405.15346"},{"key":"e_1_3_2_1_408_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1059"},{"key":"e_1_3_2_1_409_1","doi-asserted-by":"publisher","unstructured":"Xiaotian Zou Yongkang Chen and Ke Li. 2024. Is the System Message Really Important to Jailbreaks in Large Language Models? doi:10.48550\/arXiv.2402.14857","DOI":"10.48550\/arXiv.2402.14857"}],"event":{"name":"FAccT '26: The 2026 ACM Conference on Fairness, Accountability, and Transparency","location":"Montreal QC Canada","acronym":"FAccT '26","sponsor":["ACM\/SIG"]},"container-title":["Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805689.3806763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T18:21:42Z","timestamp":1782757302000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805689.3806763"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,25]]},"references-count":409,"alternative-id":["10.1145\/3805689.3806763","10.1145\/3805689"],"URL":"https:\/\/doi.org\/10.1145\/3805689.3806763","relation":{},"subject":[],"published":{"date-parts":[[2026,6,25]]},"assertion":[{"value":"2026-06-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}