{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T21:31:25Z","timestamp":1776115885894,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613905.3637135","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:15:21Z","timestamp":1715415321000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["AI Is Not Enough: A Hybrid Technical Approach to AI Adoption in UI Linting With Heuristics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0845-5563","authenticated-orcid":false,"given":"Yuwen","family":"Lu","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, University of Notre Dame, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4928-6225","authenticated-orcid":false,"given":"Tiffany","family":"Knearem","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3163-4783","authenticated-orcid":false,"given":"Shona","family":"Dutta","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1064-9768","authenticated-orcid":false,"given":"Jamie","family":"Blass","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8484-841X","authenticated-orcid":false,"given":"Clara","family":"Kliman-Silver","sequence":"additional","affiliation":[{"name":"Google, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9150-1331","authenticated-orcid":false,"given":"Frank","family":"Bentley","sequence":"additional","affiliation":[{"name":"Google, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","unstructured":"[n. d.]. Layout \u2013 Material Design 3. https:\/\/m3.material.io\/foundations\/layout\/understanding-layout\/spacing. Accessed: 2023-9-27."},{"key":"e_1_3_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533856"},{"key":"e_1_3_3_3_3_1","doi-asserted-by":"crossref","unstructured":"Diego\u00a0Martin Arroyo Janis Postels and Federico Tombari. 2021. Variational Transformer Networks for Layout Generation.","DOI":"10.1109\/CVPR46437.2021.01343"},{"key":"e_1_3_3_3_4_1","volume-title":"Automated System Testing Using Visual GUI Testing Tools: A Comparative Study in Industry. In 2012 IEEE Fifth International Conference on Software Testing, Verification and Validation. 350\u2013359","author":"Borjesson Emil","year":"2012","unstructured":"Emil Borjesson and Robert Feldt. 2012. Automated System Testing Using Visual GUI Testing Tools: A Comparative Study in Industry. In 2012 IEEE Fifth International Conference on Software Testing, Verification and Validation. 350\u2013359."},{"key":"e_1_3_3_3_5_1","volume-title":"Language Models are Few-Shot Learners. (May","author":"Brown B","year":"2020","unstructured":"Tom\u00a0B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel\u00a0M Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. (May 2020). arxiv:2005.14165\u00a0[cs.CL]"},{"key":"e_1_3_3_3_6_1","unstructured":"Jieshan Chen Amanda Swearngin Jason Wu Titus Barik Jeffrey Nichols and Xiaoyi Zhang. 2022. Extracting Replayable Interactions from Videos of Mobile App Usage."},{"key":"e_1_3_3_3_7_1","volume-title":"Towards Complete Icon Labeling in Mobile Applications. In CHI Conference on Human Factors in Computing Systems. ACM, New Orleans LA USA, 1\u201314","author":"Chen Jieshan","year":"2022","unstructured":"Jieshan Chen, Amanda Swearngin, Jason Wu, Titus Barik, Jeffrey Nichols, and Xiaoyi Zhang. 2022. Towards Complete Icon Labeling in Mobile Applications. In CHI Conference on Human Factors in Computing Systems. ACM, New Orleans LA USA, 1\u201314."},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352681"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126651"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581273"},{"key":"e_1_3_3_3_11_1","unstructured":"Weixi Feng Wanrong Zhu Tsu-Jui Fu Varun Jampani Arjun Akula Xuehai He Sugato Basu Xin\u00a0Eric Wang and William\u00a0Yang Wang. 2023. LayoutGPT: Compositional Visual Planning and Generation with Large Language Models."},{"key":"e_1_3_3_3_12_1","unstructured":"Hiroki Furuta Ofir Nachum Kuang-Huei Lee Yutaka Matsuo Shixiang\u00a0Shane Gu and Izzeddin Gur. 2023. Instruction-Finetuned Foundation Models for Multimodal Web Navigation. (2023)."},{"key":"e_1_3_3_3_13_1","volume-title":"Detecting and Preventing Hallucinations in Large Vision Language Models. (Aug","author":"Gunjal Anisha","year":"2023","unstructured":"Anisha Gunjal, Jihan Yin, and Erhan Bas. 2023. Detecting and Preventing Hallucinations in Large Vision Language Models. (Aug. 2023). arxiv:2308.06394\u00a0[cs.CV]"},{"key":"e_1_3_3_3_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_3_15_1","volume-title":"PromptMaker: Prompt-based Prototyping with Large Language Models. In Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems(CHI EA \u201922)","author":"Jiang Ellen","year":"2022","unstructured":"Ellen Jiang, Kristen Olson, Edwin Toh, Alejandra Molina, Aaron Donsbach, Michael Terry, and Carrie\u00a0J Cai. 2022. PromptMaker: Prompt-based Prototyping with Large Language Models. In Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems(CHI EA \u201922). Association for Computing Machinery, New York, NY, USA, 1\u20138."},{"key":"e_1_3_3_3_16_1","volume-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks. (May","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-Tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-augmented generation for knowledge-intensive NLP tasks. (May 2020). arxiv:2005.11401\u00a0[cs.CL]"},{"key":"e_1_3_3_3_17_1","volume-title":"Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. ACM, Yokohama Japan, 1\u201315","author":"Jia-Jun Li Toby","year":"2021","unstructured":"Toby Jia-Jun Li, Lindsay Popowski, Tom Mitchell, and Brad\u00a0A Myers. 2021. Screen2Vec: Semantic Embedding of GUI Screens and GUI Components. In Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. ACM, Yokohama Japan, 1\u201315."},{"key":"e_1_3_3_3_18_1","volume-title":"Evaluating Object Hallucination in Large Vision-Language Models. (May","author":"Li Yifan","year":"2023","unstructured":"Yifan Li, Yifan Du, Kun Zhou, Jinpeng Wang, Wayne\u00a0Xin Zhao, and Ji-Rong Wen. 2023. Evaluating Object Hallucination in Large Vision-Language Models. (May 2023). arxiv:2305.10355\u00a0[cs.CV]"},{"key":"e_1_3_3_3_19_1","volume-title":"VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling.","author":"Li Yang","year":"2021","unstructured":"Yang Li, Gang Li, Xin Zhou, Mostafa Dehghani, and Alexey Gritsenko. 2021. VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling."},{"key":"e_1_3_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.10491"},{"key":"e_1_3_3_3_21_1","volume-title":"Bridging the Gap Between UX Practitioners\u2019 Work Practices and AI-Enabled Design Support Tools. In Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems(CHI EA \u201922)","author":"Lu Yuwen","year":"2022","unstructured":"Yuwen Lu, Chengzhi Zhang, Iris Zhang, and Toby Jia-Jun Li. 2022. Bridging the Gap Between UX Practitioners\u2019 Work Practices and AI-Enabled Design Support Tools. In Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems(CHI EA \u201922). Association for Computing Machinery, New York, NY, USA, 1\u20137."},{"key":"e_1_3_3_3_22_1","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1237\/3\/032020"},{"key":"e_1_3_3_3_23_1","volume-title":"Magic Layouts: Structural Prior for Component Detection in User Interface Designs. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE","author":"Manandhar Dipu","year":"2021","unstructured":"Dipu Manandhar, Hailin Jin, and John Collomosse. 2021. Magic Layouts: Structural Prior for Component Detection in User Interface Designs. In 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, Nashville, TN, USA, 15804\u201315813."},{"key":"e_1_3_3_3_24_1","unstructured":"Lucas Memmert and Navid Tavanapour. 2023. Towards Human-AI-Collaboration in Brainstorming: Empirical Insights into the Perception of Working with a Generative AI. (2023)."},{"key":"e_1_3_3_3_25_1","volume-title":"Computational Approaches for App-to-App Retrieval and Design Consistency Check. (Sept","author":"Park Seokhyeon","year":"2023","unstructured":"Seokhyeon Park, Wonjae Kim, Young-Ho Kim, and Jinwook Seo. 2023. Computational Approaches for App-to-App Retrieval and Design Consistency Check. (Sept. 2023). arxiv:2309.10328\u00a0[cs.HC]"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3513130.3558985"},{"key":"e_1_3_3_3_27_1","volume-title":"Proceedings of the 32nd Australian Conference on Human-Computer Interaction(OzCHI \u201920)","author":"Sermuga\u00a0Pandian Vinoth\u00a0Pandian","year":"2021","unstructured":"Vinoth\u00a0Pandian Sermuga\u00a0Pandian, Sarah Suleri, Christian Beecks, and Matthias Jarke. 2021. MetaMorph: AI Assistance to Transform Lo-Fi Sketches to Higher Fidelities. In Proceedings of the 32nd Australian Conference on Human-Computer Interaction(OzCHI \u201920). Association for Computing Machinery, New York, NY, USA, 403\u2013412."},{"key":"e_1_3_3_3_28_1","volume-title":"SynZ: Enhanced Synthetic Dataset for Training UI Element Detectors. In 26th International Conference on Intelligent User Interfaces. ACM, College Station TX USA, 67\u201369","author":"Sermuga\u00a0Pandian Vinoth\u00a0Pandian","year":"2021","unstructured":"Vinoth\u00a0Pandian Sermuga\u00a0Pandian, Sarah Suleri, and Matthias Jarke. 2021. SynZ: Enhanced Synthetic Dataset for Training UI Element Detectors. In 26th International Conference on Intelligent User Interfaces. ACM, College Station TX USA, 67\u201369."},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106237.3106298"},{"key":"e_1_3_3_3_30_1","volume-title":"Building Design Systems","author":"Vesselov Sarrah","unstructured":"Sarrah Vesselov and Taurie Davis. 2019. Building Design Systems. Apress."},{"key":"e_1_3_3_3_31_1","doi-asserted-by":"crossref","unstructured":"Bryan Wang Gang Li and Yang Li. 2023. Enabling Conversational Interaction with Mobile UI using Large Language Models.","DOI":"10.1145\/3544548.3580895"},{"key":"e_1_3_3_3_32_1","doi-asserted-by":"crossref","unstructured":"Bryan Wang Gang Li Xin Zhou Zhourong Chen Tovi Grossman and Yang Li. 2021. Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning.","DOI":"10.1145\/3472749.3474765"},{"key":"e_1_3_3_3_33_1","volume-title":"Evaluation and Analysis of Hallucination in Large Vision-Language Models. (Aug","author":"Wang Junyang","year":"2023","unstructured":"Junyang Wang, Yiyang Zhou, Guohai Xu, Pengcheng Shi, Chenlin Zhao, Haiyang Xu, Qinghao Ye, Ming Yan, Ji Zhang, Jihua Zhu, Jitao Sang, and Haoyu Tang. 2023. Evaluation and Analysis of Hallucination in Large Vision-Language Models. (Aug. 2023). arxiv:2308.15126\u00a0[cs.LG]"},{"key":"e_1_3_3_3_34_1","volume-title":"Shiqi Jiang, Yunhao Liu, Yaqin Zhang, and Yunxin Liu.","author":"Wen Hao","year":"2023","unstructured":"Hao Wen, Yuanchun Li, Guohong Liu, Shanhui Zhao, Tao Yu, Toby Jia-Jun Li, Shiqi Jiang, Yunhao Liu, Yaqin Zhang, and Yunxin Liu. 2023. Empowering LLM to use Smartphone for Intelligent Task Automation."},{"key":"e_1_3_3_3_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3293882.3330551"},{"key":"e_1_3_3_3_36_1","volume-title":"Screen Correspondence: Mapping Interchangeable Elements between UIs.","author":"Wu Jason","year":"2023","unstructured":"Jason Wu, Amanda Swearngin, Xiaoyi Zhang, Jeffrey Nichols, and Jeffrey\u00a0P Bigham. 2023. Screen Correspondence: Mapping Interchangeable Elements between UIs."},{"key":"e_1_3_3_3_37_1","unstructured":"Jason Wu Siyan Wang Siman Shen Yi-Hao Peng Jeffrey Nichols and Jeffrey\u00a0P Bigham. 2023. WebUI: A Dataset for Enhancing Visual UI Understanding with Web Semantics."},{"key":"e_1_3_3_3_38_1","volume-title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models. (June","author":"Xu Peng","year":"2023","unstructured":"Peng Xu, Wenqi Shao, Kaipeng Zhang, Peng Gao, Shuo Liu, Meng Lei, Fanqing Meng, Siyuan Huang, Yu Qiao, and Ping Luo. 2023. LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models. (June 2023). arxiv:2306.09265\u00a0[cs.CV]"},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00075"},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445186"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377811.3380411"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Extended Abstracts of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613905.3637135","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613905.3637135","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:57:19Z","timestamp":1750291039000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613905.3637135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":41,"alternative-id":["10.1145\/3613905.3637135","10.1145\/3613905"],"URL":"https:\/\/doi.org\/10.1145\/3613905.3637135","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}