{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:57:54Z","timestamp":1776931074281,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,23]]},"DOI":"10.1145\/3742413.3789108","type":"proceedings-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T11:32:24Z","timestamp":1772537544000},"page":"1968-1983","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Vulnerability of LLM Outputs to Heuristics-Inducing Prompt Structures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0866-9277","authenticated-orcid":false,"given":"Toshiki","family":"Kuramoto","sequence":"first","affiliation":[{"name":"Bridgestone Corporation, Tokyo, Japan and Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1336-6961","authenticated-orcid":false,"given":"Ryohei","family":"Kamei","sequence":"additional","affiliation":[{"name":"Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2108-1340","authenticated-orcid":false,"given":"Jun","family":"Suzuki","sequence":"additional","affiliation":[{"name":"Tohoku University, Sendai, Japan; RIKEN, Tokyo, Japan and NII LLMC, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"Marah Abdin Jyoti Aneja Hany Awadalla Ahmed Awadallah et\u00a0al. 2024. Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone. arxiv:https:\/\/arXiv.org\/abs\/2404.14219\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2404.14219"},{"key":"e_1_3_3_2_3_2","unstructured":"Marah Abdin Jyoti Aneja Harkirat Behl S\u00e9bastien Bubeck Ronen Eldan Suriya Gunasekar Michael Harrison Russell\u00a0J. Hewett Mojan Javaheripi Piero Kauffmann James\u00a0R. Lee Yin\u00a0Tat Lee Yuanzhi Li Weishung Liu Caio C.\u00a0T. Mendes Anh Nguyen Eric Price Gustavo de Rosa Olli Saarikivi Adil Salim Shital Shah Xin Wang Rachel Ward Yue Wu Dingli Yu Cyril Zhang and Yi Zhang. 2024. Phi-4 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2412.08905\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.08905"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Balazs Aczel Bence Bago Aba Szollosi Andrei Foldes and Bence Lukacs. 2015. Is it time for studying real-life debiasing? Evaluation of the effectiveness of an analogical intervention technique. Frontiers in psychology 6 (2015) 1120.","DOI":"10.3389\/fpsyg.2015.01120"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"crossref","unstructured":"Juveria Afreen Mahsa Mohaghegh and Maryam Doborjeh. 2025. Systematic literature review on bias mitigation in generative AI. AI and Ethics 5 (2025) 4789\u20134841.","DOI":"10.1007\/s43681-025-00721-9"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Jungyong Ahn Jungwon Kim and Yongjun Sung. 2022. The effect of gender stereotypes on artificial intelligence recommendations. Journal of Business Research 141 (2022) 50\u201359.","DOI":"10.1016\/j.jbusres.2021.12.007"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.84"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.3"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712111"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.739"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Barbara Fasolo Claire Heard and Irene Scopelliti. 2025. Mitigating cognitive bias to improve organizational decisions: An integrative review framework and research agenda. Journal of Management 51 6 (2025) 2182\u20132211.","DOI":"10.1177\/01492063241287188"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.76"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Isabel\u00a0O. Gallegos Ryan\u00a0A. Rossi Joe Barrow Md\u00a0Mehrab Tanjim Sungchul Kim Franck Dernoncourt Tong Yu Ruiyi Zhang and Nesreen\u00a0K. Ahmed. 2024. Bias and Fairness in Large Language Models: A Survey. Computational Linguistics 50 3 (Sept. 2024) 1097\u20131179. 10.1162\/coli_a_00524","DOI":"10.1162\/coli_a_00524"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645210"},{"key":"e_1_3_3_2_15_2","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey et\u00a0al. 2024. The Llama 3 Herd of Models. arxiv:https:\/\/arXiv.org\/abs\/2407.21783\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_3_2_16_2","first-page":"21849","volume-title":"International Conference on Representation Learning","volume":"2024","author":"Gupta Shashank","year":"2024","unstructured":"Shashank Gupta, Vaishnavi Shrivastava, Ameet Deshpande, Ashwin Kalyan, Peter Clark, Ashish Sabharwal, and Tushar Khot. 2024. Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs. In International Conference on Representation Learning , B.\u00a0Kim, Y.\u00a0Yue, S.\u00a0Chaudhuri, K.\u00a0Fragkiadaki, M.\u00a0Khan, and Y.\u00a0Sun (Eds.), Vol.\u00a02024. Vienna, Austria, 21849\u201321874. https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2024\/file\/5e1a87dbb7e954b8d9d6c91f6db771eb-Paper-Conference.pdf"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Ziwei Ji Nayeon Lee Rita Frieske Tiezheng Yu Dan Su Yan Xu Etsuko Ishii Ye\u00a0Jin Bang Andrea Madotto and Pascale Fung. 2023. Survey of hallucination in natural language generation. ACM computing surveys 55 12 (2023) 1\u201338.","DOI":"10.1145\/3571730"},{"key":"e_1_3_3_2_18_2","unstructured":"Albert\u00a0Q. Jiang Alexandre Sablayrolles Antoine Roux Arthur Mensch Blanche Savary Chris Bamford Devendra\u00a0Singh Chaplot Diego de\u00a0las Casas Emma\u00a0Bou Hanna Florian Bressand Gianna Lengyel Guillaume Bour Guillaume Lample L\u00e9lio\u00a0Renard Lavaud Lucile Saulnier Marie-Anne Lachaux Pierre Stock Sandeep Subramanian Sophia Yang Szymon Antoniak Teven\u00a0Le Scao Th\u00e9ophile Gervet Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William\u00a0El Sayed. 2024. Mixtral of Experts. arxiv:https:\/\/arXiv.org\/abs\/2401.04088\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2401.04088"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712160"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Daniel Kahneman and Amos Tversky. 1973. On the psychology of prediction.Psychological review 80 4 (1973) 237.","DOI":"10.1037\/h0034747"},{"key":"e_1_3_3_2_21_2","unstructured":"Adam\u00a0Tauman Kalai Ofir Nachum Santosh\u00a0S. Vempala and Edwin Zhang. 2025. Why Language Models Hallucinate. arxiv:https:\/\/arXiv.org\/abs\/2509.04664\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2509.04664"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Takeshi Kojima Shixiang\u00a0Shane Gu Machel Reid Yutaka Matsuo and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in neural information processing systems 35 (2022) 22199\u201322213.","DOI":"10.52202\/068431-1613"},{"key":"e_1_3_3_2_23_2","series-title":"(NIPS \u201922)","volume-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems","author":"Lee Nayeon","year":"2022","unstructured":"Nayeon Lee, Wei Ping, Peng Xu, Mostofa Patwary, Pascale Fung, Mohammad Shoeybi, and Bryan Catanzaro. 2022. Factuality enhanced language models for open-ended text generation. In Proceedings of the 36th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201922). Curran Associates Inc., Red Hook, NY, USA, Article 2506, 14\u00a0pages."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Zichao Lin Shuyan Guan Wending Zhang Huiyan Zhang Yugang Li and Huaping Zhang. 2024. Towards trustworthy LLMs: a review on debiasing and dehallucinating in large language models. Artificial Intelligence Review 57 9 (2024) 243.","DOI":"10.1007\/s10462-024-10896-y"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Aman Madaan Niket Tandon Prakhar Gupta Skyler Hallinan Luyu Gao Sarah Wiegreffe Uri Alon Nouha Dziri Shrimai Prabhumoye Yiming Yang et\u00a0al. 2023. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems 36 (2023) 46534\u201346594.","DOI":"10.52202\/075280-2019"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.nlp4dh-1.50"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.173"},{"key":"e_1_3_3_2_28_2","volume-title":"Llama 3.2: Revolutionizing edge AI and vision with open, customizable models","year":"2024","unstructured":"Meta. 2024. Llama 3.2: Revolutionizing edge AI and vision with open, customizable models. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices\/"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Fabio Motoki Valdemar Pinho\u00a0Neto and Victor Rodrigues. 2024. More human than human: measuring ChatGPT political bias. Public Choice 198 1 (2024) 3\u201323.","DOI":"10.1007\/s11127-023-01097-2"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Jeremy\u00a0K. Nguyen. 2024. Human bias in AI models? Anchoring effects and mitigation strategies in large language models. Journal of Behavioral and Experimental Finance 43 (2024) 100971. 10.1016\/j.jbef.2024.100971","DOI":"10.1016\/j.jbef.2024.100971"},{"key":"e_1_3_3_2_31_2","unstructured":"OpenAI : Aaron Hurst Adam Lerer Adam\u00a0P. Goucher et\u00a0al. 2024. GPT-4o System Card. arxiv:https:\/\/arXiv.org\/abs\/2410.21276\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_3_2_32_2","unstructured":"OpenAI : Aaron Jaech Adam Kalai Adam Lerer et\u00a0al. 2024. OpenAI o1 System Card. arxiv:https:\/\/arXiv.org\/abs\/2412.16720\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2412.16720"},{"key":"e_1_3_3_2_33_2","volume-title":"OpenAI o3 and o4-mini System Card","year":"2024","unstructured":"OpenAI. 2024. OpenAI o3 and o4-mini System Card. https:\/\/openai.com\/index\/o3-o4-mini-system-card\/"},{"key":"e_1_3_3_2_34_2","volume-title":"GPT-5 System Card","year":"2025","unstructured":"OpenAI. 2025. GPT-5 System Card. https:\/\/openai.com\/index\/gpt-5-system-card\/"},{"key":"e_1_3_3_2_35_2","first-page":"250","volume-title":"Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track)","author":"Pantana Giada","year":"2024","unstructured":"Giada Pantana, Marta Castello, and Ilaria Torre. 2024. Examining Cognitive Biases in ChatGPT 3.5 and ChatGPT 4 through Human Evaluation and Linguistic Comparison. In Proceedings of the 16th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), Rebecca Knowles, Akiko Eriguchi, and Shivali Goel (Eds.). Association for Machine Translation in the Americas, Chicago, USA, 250\u2013260. https:\/\/aclanthology.org\/2024.amta-research.21\/"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713714"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Yao Qu and Jue Wang. 2024. Performance and biases of large language models in public opinion simulation. Humanities and Social Sciences Communications 11 1 (2024) 1\u201313.","DOI":"10.1057\/s41599-024-03609-x"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.92"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-90913-0_1"},{"key":"e_1_3_3_2_40_2","first-page":"72044","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Salewski Leonard","year":"2023","unstructured":"Leonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz, and Zeynep Akata. 2023. In-Context Impersonation Reveals Large Language Models'Strengths and Biases. In Advances in Neural Information Processing Systems , A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine (Eds.), Vol.\u00a036. Curran Associates, Inc., Vancouver, Canada, 72044\u201372057. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/e3fe7b34ba4f378df39cb12a97193f41-Paper-Conference.pdf"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Sandeep\u00a0Singh Sengar Affan\u00a0Bin Hasan Sanjay Kumar and Fiona Carroll. 2025. Generative artificial intelligence: a systematic review and applications. Multimedia Tools and Applications 84 21 (2025) 23661\u201323700.","DOI":"10.1007\/s11042-024-20016-1"},{"key":"e_1_3_3_2_42_2","unstructured":"Veda\u00a0C Storey Wei\u00a0Thoo Yue J\u00a0Leon Zhao and Roman Lukyanenko. 2025. Generative artificial intelligence: Evolving technology growing societal impact and opportunities for information systems research. Information Systems Frontiers (2025) 1\u201322."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Gaurav Suri Lily\u00a0R Slater Ali Ziaee and Morgan Nguyen. 2024. Do large language models show decision heuristics similar to humans? A case study using GPT-3.5.Journal of Experimental Psychology: General 153 4 (2024) 1066.","DOI":"10.1037\/xge0001547"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.240"},{"key":"e_1_3_3_2_45_2","unstructured":"Alaina\u00a0N. Talboy and Elizabeth Fuller. 2023. Challenging the appearance of machine intelligence: Cognitive bias in LLMs and Best Practices for Adoption. arxiv:https:\/\/arXiv.org\/abs\/2304.01358\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2304.01358"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-srw.11"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-56972-2_2"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Amos Tversky and Daniel Kahneman. 1974. Judgment under Uncertainty: Heuristics and Biases. Science 185 4157 (1974) 1124\u20131131. http:\/\/www.jstor.org\/stable\/1738360","DOI":"10.1126\/science.185.4157.1124"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","unstructured":"Amos Tversky and Daniel Kahneman. 1981. The Framing of Decisions and the Psychology of Choice. Science 211 4481 (1981) 453\u2013458. 10.1126\/science.7455683","DOI":"10.1126\/science.7455683"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"crossref","unstructured":"Amos Tversky and Daniel Kahneman. 1983. Extensional versus intuitive reasoning: The conjunction fallacy in probability judgment.Psychological review 90 4 (1983) 293.","DOI":"10.1037\/0033-295X.90.4.293"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.399"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Eva\u00a0AM Van\u00a0Dis Johan Bollen Willem Zuidema Robert Van\u00a0Rooij and Claudi\u00a0L Bockting. 2023. ChatGPT: five priorities for research. Nature 614 7947 (2023) 224\u2013226.","DOI":"10.1038\/d41586-023-00288-7"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Ji Wu Yaokang Song and Doris\u00a0Chenguang Wu. 2024. Does ChatGPT show gender bias in behavior detection?Humanities and Social Sciences Communications 11 1 (2024) 1\u20138.","DOI":"10.1057\/s41599-024-04219-3"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","unstructured":"Weijia Xu Sweta Agrawal Eleftheria Briakou Marianna\u00a0J. Martindale and Marine Carpuat. 2023. Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection. Transactions of the Association for Computational Linguistics 11 (2023) 546\u2013564. 10.1162\/tacl_a_00563","DOI":"10.1162\/tacl_a_00563"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3657054.3664243"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.256"},{"key":"e_1_3_3_2_57_2","volume-title":"First Conference on Language Modeling","author":"Zhu Banghua","year":"2024","unstructured":"Banghua Zhu, Evan Frick, Tianhao Wu, Hanlin Zhu, Karthik Ganesan, Wei-Lin Chiang, Jian Zhang, and Jiantao Jiao. 2024. Starling-7b: Improving helpfulness and harmlessness with rlaif. In First Conference on Language Modeling. Philadelphia, USA."}],"event":{"name":"IUI '26: 31st International Conference on Intelligent User Interfaces","location":"Paphos Cyprus","acronym":"IUI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the 31st International Conference on Intelligent User Interfaces"],"original-title":[],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T13:02:26Z","timestamp":1773493346000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3742413.3789108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":56,"alternative-id":["10.1145\/3742413.3789108","10.1145\/3742413"],"URL":"https:\/\/doi.org\/10.1145\/3742413.3789108","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"}}]}}