{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T04:04:42Z","timestamp":1751169882490,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","funder":[{"name":"FWO","award":["1247125N"],"award-info":[{"award-number":["1247125N"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,16]]},"DOI":"10.1145\/3708319.3733656","type":"proceedings-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T15:17:00Z","timestamp":1749741420000},"page":"237-242","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["What If the Prompt Were Different? Counterfactual Explanations for the Characteristics of Generative Outputs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3784-826X","authenticated-orcid":false,"given":"Sofie","family":"Goethals","sequence":"first","affiliation":[{"name":"University of Antwerp, Antwerp, Belgium"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6369-3711","authenticated-orcid":false,"given":"Joao","family":"Sedoc","sequence":"additional","affiliation":[{"name":"NYU Stern, New York, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0307-3884","authenticated-orcid":false,"given":"Foster","family":"Provost","sequence":"additional","affiliation":[{"name":"NYU Stern, New York, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,6,12]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3461702.3462624"},{"key":"e_1_3_3_2_3_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_2_4_2","unstructured":"Sotiris Anagnostidis and Jannis Bulian. 2024. How Susceptible are LLMs to Influence in Prompts? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.11865 (2024)."},{"key":"e_1_3_3_2_5_2","unstructured":"AI Anthropic. 2024. The claude 3 model family: Opus sonnet haiku. Claude-3 Model Card 1 (2024)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Shikha Bordia and Samuel\u00a0R Bowman. 2019. Identifying and reducing gender bias in word-level language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1904.03035 (2019).","DOI":"10.18653\/v1\/N19-3002"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Jin Chen Zheng Liu Xu Huang Chenwang Wu Qi Liu Gangwei Jiang Yuanhao Pu Yuxuan Lei Xiaolong Chen Xingmei Wang et\u00a0al. 2024. When large language models meet personalization: Perspectives of challenges and opportunities. World Wide Web 27 4 (2024) 42.","DOI":"10.1007\/s11280-024-01276-1"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","unstructured":"Shauna Concannon and Marcus Tomalin. 2024. Measuring perceived empathy in dialogue systems. Ai & Society 39 5 (2024) 2233\u20132247.","DOI":"10.1007\/s00146-023-01715-z"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Badhan\u00a0Chandra Das M\u00a0Hadi Amini and Yanzhao Wu. 2025. Security and privacy challenges of large language models: A survey. Comput. Surveys 57 6 (2025) 1\u201339.","DOI":"10.1145\/3712001"},{"key":"e_1_3_3_2_10_2","unstructured":"Esin Durmus Karina Nguyen Thomas\u00a0I Liao Nicholas Schiefer Amanda Askell Anton Bakhtin Carol Chen Zac Hatfield-Dodds Danny Hernandez Nicholas Joseph et\u00a0al. 2023. Towards measuring the representation of subjective global opinions in language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.16388 (2023)."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-short.39"},{"key":"e_1_3_3_2_12_2","unstructured":"Md\u00a0Meftahul Ferdaus Mahdi Abdelguerfi Elias Ioup Kendall\u00a0N Niles Ken Pathak and Steven Sloan. 2024. Towards trustworthy ai: A review of ethical and robust large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.13934 (2024)."},{"key":"e_1_3_3_2_13_2","unstructured":"Carlos Fern\u00e1ndez-Lor\u00eda Foster Provost and Xintian Han. 2022. Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach. MIS Quarterly 46 3 (2022)."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533202"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Stefan Feuerriegel Jochen Hartmann Christian Janiesch and Patrick Zschech. 2024. Generative ai. Business & Information Systems Engineering 66 1 (2024) 111\u2013126.","DOI":"10.1007\/s12599-023-00834-7"},{"key":"e_1_3_3_2_16_2","unstructured":"Luke Friedman Sameer Ahuja David Allen Zhenning Tan Hakim Sidahmed Changbo Long Jun Xie Gabriel Schubiner Ajay Patel Harsh Lara et\u00a0al. 2023. Leveraging large language models in conversational recommender systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.07961 (2023)."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Sofie Goethals David Martens and Toon Calders. 2024. PreCoF: counterfactual explanations for fairness. Machine Learning 113 5 (2024) 3111\u20133142.","DOI":"10.1007\/s10994-023-06319-8"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Carlos G\u00f3mez-Rodr\u00edguez and Paul Williams. 2023. A confederacy of models: A comprehensive evaluation of LLMs on creative writing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.08433 (2023).","DOI":"10.18653\/v1\/2023.findings-emnlp.966"},{"key":"e_1_3_3_2_19_2","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Riccardo Guidotti Anna Monreale Salvatore Ruggieri Franco Turini Fosca Giannotti and Dino Pedreschi. 2018. A survey of methods for explaining black box models. ACM computing surveys (CSUR) 51 5 (2018) 1\u201342.","DOI":"10.1145\/3236009"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"David Gunning Mark Stefik Jaesik Choi Timothy Miller Simone Stumpf and Guang-Zhong Yang. 2019. XAI\u2014Explainable artificial intelligence. Science robotics 4 37 (2019) eaay7120.","DOI":"10.1126\/scirobotics.aay7120"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Thomas Hartvigsen Saadia Gabriel Hamid Palangi Maarten Sap Dipankar Ray and Ece Kamar. 2022. Toxigen: A large-scale machine-generated dataset for adversarial and implicit hate speech detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.09509 (2022).","DOI":"10.18653\/v1\/2022.acl-long.234"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Lei Huang Weijiang Yu Weitao Ma Weihong Zhong Zhangyin Feng Haotian Wang Qianglong Chen Weihua Peng Xiaocheng Feng Bing Qin et\u00a0al. 2025. A survey on hallucination in large language models: Principles taxonomy challenges and open questions. ACM Transactions on Information Systems 43 2 (2025) 1\u201355.","DOI":"10.1145\/3703155"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Enkelejda Kasneci Kathrin Se\u00dfler Stefan K\u00fcchemann Maria Bannert Daryna Dementieva Frank Fischer Urs Gasser Georg Groh Stephan G\u00fcnnemann Eyke H\u00fcllermeier et\u00a0al. 2023. ChatGPT for good? On opportunities and challenges of large language models for education. Learning and individual differences 103 (2023) 102274.","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582269.3615599"},{"key":"e_1_3_3_2_26_2","unstructured":"Tingting Liu Salvatore Giorgi Ankit Aich Allison Lahnala Brenda Curtis Lyle Ungar and Jo\u00e3o Sedoc. 2024. The illusion of empathy: How ai chatbots shape conversation perception. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.12877 (2024)."},{"key":"e_1_3_3_2_27_2","unstructured":"Edward Loper and Steven Bird. 2002. Nltk: The natural language toolkit. arXiv preprint cs\/0205028 (2002)."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"David Martens and Foster Provost. 2014. Explaining data-driven document classifications. MIS quarterly 38 1 (2014) 73\u2013100.","DOI":"10.25300\/MISQ\/2014\/38.1.04"},{"key":"e_1_3_3_2_29_2","unstructured":"Behnam Mohammadi. 2024. Explaining Large Language Models Decisions Using Shapley Values. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.01332 (2024)."},{"key":"e_1_3_3_2_30_2","volume-title":"Interpretable machine learning","author":"Molnar Christoph","year":"2020","unstructured":"Christoph Molnar. 2020. Interpretable machine learning. Lulu. com."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Ethan Perez Saffron Huang Francis Song Trevor Cai Roman Ring John Aslanides Amelia Glaese Nat McAleese and Geoffrey Irving. 2022. Red teaming language models with language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2202.03286 (2022).","DOI":"10.18653\/v1\/2022.emnlp-main.225"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Rohit Raj Arpit Singh Vimal Kumar and Pratima Verma. 2023. Analyzing the potential benefits and use cases of ChatGPT as a tool for improving the efficiency and effectiveness of business operations. BenchCouncil Transactions on Benchmarks Standards and Evaluations 3 3 (2023) 100140.","DOI":"10.1016\/j.tbench.2023.100140"},{"key":"e_1_3_3_2_33_2","unstructured":"Paulius Rauba Qiyao Wei and Mihaela van\u00a0der Schaar. 2024. Quantifying perturbation impacts for large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.00868 (2024)."},{"key":"e_1_3_3_2_34_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Ravfogel Shauli","year":"2025","unstructured":"Shauli Ravfogel, Anej Svete, V\u00e9steinn Sn\u00e6bjarnarson, and Ryan Cotterell. 2025. Gumbel Counterfactual Generation From Language Models. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Aadesh Salecha Molly\u00a0E Ireland Shashanka Subrahmanya Jo\u00e3o Sedoc Lyle\u00a0H Ungar and Johannes\u00a0C Eichstaedt. 2024. Large language models display human-like social desirability biases in Big Five personality surveys. PNAS nexus 3 12 (2024) pgae533.","DOI":"10.1093\/pnasnexus\/pgae533"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Karan Singhal Shekoofeh Azizi Tao Tu S\u00a0Sara Mahdavi Jason Wei Hyung\u00a0Won Chung Nathan Scales Ajay Tanwani Heather Cole-Lewis Stephen Pfohl et\u00a0al. 2023. Large language models encode clinical knowledge. Nature 620 7972 (2023) 172\u2013180.","DOI":"10.1038\/s41586-023-06291-2"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Ruixiang Tang Dehan Kong Longtao Huang and Hui Xue. 2023. Large language models can be lazy learners: Analyze shortcuts in in-context learning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.17256 (2023).","DOI":"10.18653\/v1\/2023.findings-acl.284"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Tom Vermeire Dieter Brughmans Sofie Goethals Raphael Mazzine\u00a0Barbossa De\u00a0Oliveira and David Martens. 2022. Explainable image classification with evidence counterfactual. Pattern Analysis and Applications 25 2 (2022) 315\u2013335.","DOI":"10.1007\/s10044-021-01055-y"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Sandra Wachter Brent Mittelstadt and Chris Russell. 2017. Counterfactual explanations without opening the black box: Automated decisions and the GDPR. Harv. JL & Tech. 31 (2017) 841.","DOI":"10.2139\/ssrn.3063289"},{"key":"e_1_3_3_2_40_2","unstructured":"Tongshuang Wu Marco\u00a0Tulio Ribeiro Jeffrey Heer and Daniel\u00a0S Weld. 2021. Polyjuice: Generating counterfactuals for explaining evaluating and improving models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2101.00288 (2021)."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Haiyan Zhao Hanjie Chen Fan Yang Ninghao Liu Huiqi Deng Hengyi Cai Shuaiqiang Wang Dawei Yin and Mengnan Du. 2024. Explainability for large language models: A survey. ACM Transactions on Intelligent Systems and Technology 15 2 (2024) 1\u201338.","DOI":"10.1145\/3639372"}],"event":{"name":"UMAP '25: 33rd ACM Conference on User Modeling, Adaptation and Personalization","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"New York City USA","acronym":"UMAP '25"},"container-title":["Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708319.3733656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T11:16:30Z","timestamp":1751109390000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708319.3733656"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,12]]},"references-count":40,"alternative-id":["10.1145\/3708319.3733656","10.1145\/3708319"],"URL":"https:\/\/doi.org\/10.1145\/3708319.3733656","relation":{},"subject":[],"published":{"date-parts":[[2025,6,12]]},"assertion":[{"value":"2025-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}