{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:55:17Z","timestamp":1781769317017,"version":"3.54.5"},"reference-count":58,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["251654672\u2014TRR 161"],"award-info":[{"award-number":["251654672\u2014TRR 161"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Case studies are central to evaluating visualization research as they provide evidence for how the developed approaches support real users, real analytical work, and real data. Conducting such studies can be challenging, since target users with relevant domain expertise are often scarce or even entirely unavailable, while the visualization researchers may lack the required expertise to perform the evaluation themselves. Current research on Large Language Models (LLMs) has shown their strong reasoning ability and usefulness in domain\u2010specific downstream tasks, provoking the question: to what degree and with what capacity can LLMs fill the role of the target users in visualization case studies? We investigate this question by evaluating how LLMs can participate across different phases of visualization case studies. We propose a conceptual framework that explores the different levels of LLM involvement and potential roles when simulating target users. To sketch where the LLM substitution is most plausible, we embed our suggested integration of LLMs within the nested model for visualization theory and design. For evaluation, we replicate case studies from published and unpublished visualization research using multiple state\u2010of\u2010the\u2010art LLMs and compare the model\u2010generated insights to those reported in the papers. Our results show that LLMs can often generate plausible and sometimes even novel interpretations of visual patterns when used for result analysis and validation, but can also struggle when highly contextual, domain\u2010specific knowledge is required.<\/jats:p>","DOI":"10.1111\/cgf.70446","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:33:07Z","timestamp":1781767987000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Can LLMs Simulate Target Users in Visualization Case Studies?"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3204-9231","authenticated-orcid":false,"given":"Jena","family":"Satkunarajan","sequence":"first","affiliation":[{"name":"University of Stuttgart  Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4630-7916","authenticated-orcid":false,"given":"Moataz","family":"Abdelaal","sequence":"additional","affiliation":[{"name":"University of Stuttgart  Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8123-8330","authenticated-orcid":false,"given":"Steffen","family":"Koch","sequence":"additional","affiliation":[{"name":"University of Stuttgart  Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4919-4582","authenticated-orcid":false,"given":"Kuno","family":"Kurzhals","sequence":"additional","affiliation":[{"name":"University of Stuttgart  Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1174-1026","authenticated-orcid":false,"given":"Daniel","family":"Weiskopf","sequence":"additional","affiliation":[{"name":"University of Stuttgart  Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"e_1_2_10_2_2","doi-asserted-by":"crossref","unstructured":"Arias\u2010Hern\u00e1ndezR. KaastraL. GreenT. M. FisherB.: Pair analytics: Capturing reasoning processes in collaborative visual analytics. In44th Hawaii International International Conference on Systems Science(2011) pp.1\u201310. doi:10.1109\/HICSS.2011.339. 5","DOI":"10.1109\/HICSS.2011.339"},{"key":"e_1_2_10_3_2","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.35179"},{"key":"e_1_2_10_4_2","doi-asserted-by":"crossref","unstructured":"BeasleyC. AbouziedA.: Pipe(line) dreams: Fully automated end\u2010to\u2010end analysis and visualization. InProceedings of the 2024 Workshop on Human\u2010In\u2010the\u2010Loop Data Analytics(2024) pp.1\u20137. doi:10.1145\/3665939.3665962. 2","DOI":"10.1145\/3665939.3665962"},{"key":"e_1_2_10_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3326698"},{"key":"e_1_2_10_6_2","doi-asserted-by":"crossref","unstructured":"BrownB. ReevesS. SherwoodS.: Into the wild: challenges and opportunities for field trial methods. InProceedings of the SIGCHI Conference on Human Factors in Computing Systems(2011) pp.1657\u20131666. doi:10.1145\/1978942.1979185. 4","DOI":"10.1145\/1978942.1979185"},{"key":"e_1_2_10_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456155"},{"key":"e_1_2_10_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.226"},{"key":"e_1_2_10_9_2","doi-asserted-by":"crossref","unstructured":"ChenY. FuQ. YuanY. WenZ. FanG. LiuD. ZhangD. LiZ. XiaoY.: Hallucination detection: Robustly discerning reliable answers in large language models. InProceedings of the 32nd ACM International Conference on Information and Knowledge Management(2023) pp.245\u2013255. doi:10.1145\/3583780.3614905. 4","DOI":"10.1145\/3583780.3614905"},{"key":"e_1_2_10_10_2","doi-asserted-by":"crossref","unstructured":"ChengL. LiX. BingL.: Is GPT\u20104 a good data analyst? InFindings of the Association for Computational Linguistics(2023) pp.9496\u20139514. doi:10.18653\/v1\/2023.findings\u2010emnlp.637. 3","DOI":"10.18653\/v1\/2023.findings-emnlp.637"},{"key":"e_1_2_10_11_2","doi-asserted-by":"publisher","DOI":"10.1037\/0003\u2010066X.49.12.997"},{"key":"e_1_2_10_12_2","doi-asserted-by":"crossref","unstructured":"ChenZ. ZhangC. WangQ. TroidlJ. WarcholS. BeyerJ. GehlenborgN. PfisterH.: Beyond generating code: Evaluating GPT on a data visualization course. InIEEE VIS Workshop on Visualization Education Literacy and Activities(2023) pp.16\u201321. doi:10.1109\/EduVis60792.2023.00009. 2","DOI":"10.1109\/EduVis60792.2023.00009"},{"key":"e_1_2_10_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456320"},{"key":"e_1_2_10_14_2","doi-asserted-by":"crossref","unstructured":"DibiaV.: LIDA: A tool for automatic generation of grammar\u2010agnostic visualizations and infographics using large language models. InProceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)(2023) pp.113\u2013126. doi:10.18653\/v1\/2023.acl\u2010demo.11. 2","DOI":"10.18653\/v1\/2023.acl-demo.11"},{"key":"e_1_2_10_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3634813"},{"key":"e_1_2_10_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3770071"},{"key":"e_1_2_10_17_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjmed\u20102025\u2010001623"},{"key":"e_1_2_10_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/1993060.1993065"},{"key":"e_1_2_10_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2025.104246"},{"key":"e_1_2_10_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3536358"},{"key":"e_1_2_10_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2013.126"},{"key":"e_1_2_10_22_2","doi-asserted-by":"crossref","unstructured":"JiZ. YuT. XuY. LeeN. IshiiE. FungP.: Towards mitigating LLM hallucination via self reflection. InFindings of the Association for Computational Linguistics(2023) pp.1827\u20131843. doi:10.18653\/v1\/2023.findings\u2010emnlp.123. 5","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"e_1_2_10_23_2","doi-asserted-by":"crossref","unstructured":"KapaniaS. AgnewW. EslamiM. HeidariH. FoxS. E.: Simulacrum of stories: Examining large language models as qualitative research participants. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems(2025) pp.489:1\u2013489:17. doi:10.1145\/3706598.3713220. 3","DOI":"10.1145\/3706598.3713220"},{"key":"e_1_2_10_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3745768"},{"key":"e_1_2_10_25_2","doi-asserted-by":"crossref","unstructured":"KlineR. B.:What's wrong with statistical tests\u2013and where we go from here. InBeyond Significance Testing: Reforming Data Analysis Methods in Behavioral Research KlineR. B. (Ed.). American Psychological Association 2004 ch. 3 pp.61\u201391. doi:10.1037\/10693\u2010003. 4","DOI":"10.1037\/10693-003"},{"key":"e_1_2_10_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3209451"},{"key":"e_1_2_10_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.279"},{"key":"e_1_2_10_28_2","doi-asserted-by":"crossref","unstructured":"LiuC. DaC. LongX. YangY. ZhangY. WangY.: SimVecVis: A dataset for enhancing MLLMs in visualization understanding. In2025 IEEE Visualization and Visual Analytics(2025) pp.26\u201330. doi:10.1109\/VIS60296.2025.00010. 2","DOI":"10.1109\/VIS60296.2025.00010"},{"key":"e_1_2_10_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3634821"},{"key":"e_1_2_10_30_2","unstructured":"LiZ. MiaoH. PascucciV. LiuS.: Visualization literacy of multimodal large language models: A comparative study.Computing Research Repository abs\/2407.10996(2024). doi:10.48550\/ARXIV.2407.10996. 2"},{"key":"e_1_2_10_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456333"},{"key":"e_1_2_10_32_2","doi-asserted-by":"crossref","unstructured":"LiV. R. SunJ. WattenbergM.: Does visualization help AI understand data? In2025 IEEE Visualization and Visual Analytics(2025) pp.51\u201355. doi:10.1109\/VIS60296.2025.00016. 2","DOI":"10.1109\/VIS60296.2025.00016"},{"key":"e_1_2_10_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3634249"},{"key":"e_1_2_10_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3274199"},{"key":"e_1_2_10_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2009.111"},{"key":"e_1_2_10_36_2","unstructured":"NoriH. KingN. McKinneyS. M. CarignanD. HorvitzE.: Capabilities of GPT\u20104 on medical challenge problems.Computing Research Repository abs\/2303.13375(2023). doi:10.48550\/arXiv.2303.13375. 3"},{"key":"e_1_2_10_37_2","doi-asserted-by":"publisher","DOI":"10.1177\/001139292040001004"},{"key":"e_1_2_10_38_2","doi-asserted-by":"crossref","unstructured":"RashikM. FeketeJ.\u2010D. MahyarN.: CLAImate: AI\u2010enabled climate change communication through personalized and localized narrative visualizations. In2025 IEEE Visualization and Visual Analytics(2025) pp.36\u201340. doi:10.1109\/VIS60296.2025.00012. 2","DOI":"10.1109\/VIS60296.2025.00012"},{"key":"e_1_2_10_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3231230"},{"key":"e_1_2_10_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3634820"},{"key":"e_1_2_10_41_2","doi-asserted-by":"publisher","DOI":"10.18419\/DARUS\u20105882"},{"key":"e_1_2_10_42_2","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14841"},{"key":"e_1_2_10_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3579700"},{"key":"e_1_2_10_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2012.213"},{"key":"e_1_2_10_45_2","doi-asserted-by":"crossref","unstructured":"ShneidermanB. PlaisantC.: Strategies for evaluating information visualization tools: Multi\u2010dimensional in\u2010depth long\u2010term case studies. InProceedings of the AVI Workshop on BEyond Time and Errors: Novel Evaluation Methods for Information Visualization(2006). doi:10.1145\/1168149.1168158. 3 4","DOI":"10.1145\/1168149.1168158"},{"key":"e_1_2_10_46_2","doi-asserted-by":"crossref","unstructured":"SatkunarajanJ. RiessJ. FrankeM. KochS.: Visual analysis of document editing patterns. InProceedings of the 18th International Symposium on Visual Information Communication and Interaction(2025) pp.4:1\u20134:8. doi:10.1145\/3769534.3769556. 8","DOI":"10.1145\/3769534.3769556"},{"key":"e_1_2_10_47_2","doi-asserted-by":"crossref","unstructured":"SrinivasanA. SetlurV. SatyanarayanA.: Pluto: Authoring semantically aligned text and charts for data\u2010driven communication. InProceedings of the 30th International Conference on Intelligent User Interfaces(2025) pp.1123\u20131140. doi:10.1145\/3708359.3712122. 2","DOI":"10.1145\/3708359.3712122"},{"key":"e_1_2_10_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3368621"},{"key":"e_1_2_10_49_2","doi-asserted-by":"crossref","unstructured":"WangH. W. BirnbaumL. SetlurV.: Jupybara: Operationalizing a design space for actionable data analysis and storytelling with LLMs. InProceedings of the 2025 CHI Conference on Human Factors in Computing Systems(2025) pp.1005:1\u20131005:24. doi:10.1145\/3706598.3713913. 3","DOI":"10.1145\/3706598.3713913"},{"key":"e_1_2_10_50_2","doi-asserted-by":"crossref","unstructured":"WeiskopfD.: Bridging quantitative and qualitative methods for visualization research: A data\/semantics perspective in light of advanced AI. InProceedings of the Workshop on Evaluation and Beyond \u2013 Methodological Approaches for Visualization(2024) pp.119\u2013128. doi:10.1109\/BELIV64461.2024.00019. 3","DOI":"10.1109\/BELIV64461.2024.00019"},{"key":"e_1_2_10_51_2","unstructured":"WhiteJ. FuQ. HaysS. SandbornM. OleaC. GilbertH. ElnasharA. Spencer\u2010SmithJ. SchmidtD. C.: A prompt pattern catalog to enhance prompt engineering with ChatGPT. InProceedings of the 30th Conference on Pattern Languages of Programs(2023) pp.5:1\u20135:31. 5"},{"key":"e_1_2_10_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456378"},{"key":"e_1_2_10_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3633869"},{"key":"e_1_2_10_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654992"},{"key":"e_1_2_10_55_2","volume-title":"Case Study Research: Design and Methods","author":"Yin R. K.","year":"2009"},{"key":"e_1_2_10_56_2","unstructured":"ZhengL. ChiangW.\u2010L. ShengY. ZhuangS. WuZ. ZhuangY. LinZ. LiZ. LiD. XingE. P. ZhangH. GonzalezJ. E. StoicaI.: Judging LLM\u2010as\u2010a\u2010judge with MT\u2010bench and Chatbot Arena. InProceedings of the 37th International Conference on Neural Information Processing Systems(2023). 2"},{"key":"e_1_2_10_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3316469"},{"key":"e_1_2_10_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3633883"},{"key":"e_1_2_10_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3368060"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70446","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70446","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T07:33:36Z","timestamp":1781768016000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70446"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":58,"alternative-id":["10.1111\/cgf.70446"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70446","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]},"assertion":[{"value":"2026-06-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70446"}}