{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T08:00:26Z","timestamp":1776931226401,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":92,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772318.3791725","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T04:12:36Z","timestamp":1776053556000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5135-8136","authenticated-orcid":false,"given":"Aeree","family":"Cho","sequence":"first","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3845-9463","authenticated-orcid":false,"given":"Grace C.","family":"Kim","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5317-2991","authenticated-orcid":false,"given":"Alexander","family":"Karpekov","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1950-5004","authenticated-orcid":false,"given":"Seongmin","family":"Lee","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8846-6460","authenticated-orcid":false,"given":"Alec","family":"Helbling","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5218-3185","authenticated-orcid":false,"given":"Benjamin","family":"Hoover","sequence":"additional","affiliation":[{"name":"IBM Research AI, Cambridge, USA and Georgia Tech, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4360-1423","authenticated-orcid":false,"given":"Zijie J.","family":"Wang","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0291-6026","authenticated-orcid":false,"given":"Minsuk","family":"Kahng","sequence":"additional","affiliation":[{"name":"Yonsei University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9824-3323","authenticated-orcid":false,"given":"Duen Horng (Polo)","family":"Chau","sequence":"additional","affiliation":[{"name":"Georgia Tech, Atlanta, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"3Blue1Brown. 2024. But what is a GPT? Visual intro to transformers. https:\/\/youtu.be\/wjZofJX0v4M."},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02072"},{"key":"e_1_3_3_3_4_2","unstructured":"Jay Alammar. 2018. The Illustrated Transformer. https:\/\/jalammar.github.io\/illustrated-transformer\/."},{"key":"e_1_3_3_3_5_2","unstructured":"Emmanuel Ameisen Jack Lindsey Adam Pearce Wes Gurnee Nicholas\u00a0L. Turner Brian Chen Craig Citro David Abrahams Shan Carter Basil Hosmer Jonathan Marcus Michael Sklar Adly Templeton Trenton Bricken Callum McDougall Hoagy Cunningham Thomas Henighan Adam Jermyn Andy Jones Andrew Persic Zhenyi Qi T. Ben\u00a0Thompson Sam Zimmerman Kelley Rivoire Thomas Conerly Chris Olah and Joshua Batson. 2025. Circuit Tracing: Revealing Computational Graphs in Language Models. Transformer Circuits Thread (2025). https:\/\/transformer-circuits.pub\/2025\/attribution-graphs\/methods.html"},{"key":"e_1_3_3_3_6_2","unstructured":"Joris Baan Maartje ter Hoeve Marlies van\u00a0der Wees Anne Schuth and M. de Rijke. 2019. Understanding Multi-Head Attention in Abstractive Summarization. ArXiv abs\/1911.03898 (2019). https:\/\/api.semanticscholar.org\/CorpusID:207853291"},{"key":"e_1_3_3_3_7_2","unstructured":"Nora Belrose Zach Furman Logan Smith Danny Halawi Igor Ostrovsky Lev McKinney Stella Biderman and Jacob Steinhardt. 2023. Eliciting latent predictions from transformers with the tuned lens. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08112 (2023)."},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3442188.3445922"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Michael Bostock Vadim Ogievetsky and Jeffrey Heer. 2011. D3 data-driven documents. IEEE transactions on visualization and computer graphics 17 12 (2011) 2301\u20132309.","DOI":"10.1109\/TVCG.2011.185"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative Research in Psychology 3 2 (2006) 77\u2013101. 10.1191\/1478088706qp063oa","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/IV51561.2020.00051"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"N.\u00a0E. Breslow and D.\u00a0G. Clayton. 1993. Approximate Inference in Generalized Linear Mixed Models. J. Amer. Statist. Assoc. 88 421 (1993) 9\u201325. http:\/\/www.jstor.org\/stable\/2290687","DOI":"10.1080\/01621459.1993.10594284"},{"key":"e_1_3_3_3_13_2","unstructured":"Brendan Bycroft. [n. d.]. LLM Visualization. https:\/\/bbycroft.net\/llm."},{"key":"e_1_3_3_3_14_2","unstructured":"Chen Chen Jinbin Huang Ethan Remsberg and Zhicheng Liu. 2024. A Visual Tour to Empirical Neural Network Robustness. https:\/\/cchen-vis.github.io\/Narrative-Viz-for-Neural-Network-Robustness\/."},{"key":"e_1_3_3_3_15_2","volume-title":"https:\/\/visxai-dimensionality-reduction-1dbad0a67a092b007c526a45.vercel.app\/1st Workshop on Visualization for AI Explainability (VISxAI)","author":"Conlen Matthew","year":"2018","unstructured":"Matthew Conlen and Fred Hohman. 2018. The Beginner\u2019s Guide to Dimensionality Reduction. https:\/\/visxai-dimensionality-reduction-1dbad0a67a092b007c526a45.vercel.app\/. In 1st Workshop on Visualization for AI Explainability (VISxAI)."},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","unstructured":"Lee\u00a0J. Cronbach. 1951. Coefficient Alpha and the Internal Structure of Tests. Psychometrika 16 3 (1951) 297\u2013334. 10.1007\/BF02310555","DOI":"10.1007\/BF02310555"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Carol\u00a0Azumah Dennis. 2015. Blogging as public pedagogy: Creating alternative educational futures. International journal of lifelong education 34 3 (2015) 284\u2013299.","DOI":"10.1080\/02601370.2014.1000408"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Joseph\u00a0F DeRose Jiayao Wang and Matthew Berger. 2020. Attention flows: Analyzing and comparing attention mechanisms in language models. IEEE Transactions on Visualization and Computer Graphics 27 2 (2020) 1160\u20131170.","DOI":"10.1109\/TVCG.2020.3028976"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Louis Deslauriers Logan\u00a0S McCarty Kelly Miller Kristina Callaghan and Greg Kestin. 2019. Measuring actual learning versus feeling of learning in response to being actively engaged in the classroom. Proceedings of the National Academy of Sciences 116 39 (2019) 19251\u201319257.","DOI":"10.1073\/pnas.1821936116"},{"key":"e_1_3_3_3_20_2","unstructured":"ONNX\u00a0Runtime developers. 2021. ONNX Runtime. https:\/\/onnxruntime.ai\/. Version: x.y.z."},{"key":"e_1_3_3_3_21_2","volume-title":"NeurIPS","author":"Dutta Subhabrata","year":"2021","unstructured":"Subhabrata Dutta, Tanya Gautam, Soumen Chakrabarti, and Tanmoy Chakraborty. 2021. Redesigning the Transformer Architecture with Insights from Multi-particle Dynamical Systems. In NeurIPS. https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/2bd388f731f26312bfc0fe30da009595-Paper.pdf"},{"key":"e_1_3_3_3_22_2","unstructured":"Nelson Elhage et\u00a0al. 2021. A Mathematical Framework for Transformer Circuits. Transformer Circuits Thread (2021)."},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","unstructured":"Enqi Fan Matt Bower and Jens Siemon. 2024. Video Tutorials in the Traditional Classroom: The Effects on Different Types of Cognitive Load. Technology Knowledge and Learning 29 4 (Dec. 2024) 2017\u20132036. 10.1007\/s10758-024-09754-1","DOI":"10.1007\/s10758-024-09754-1"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.965"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Eric Fouh Monika Akbar and Clifford A.\u00a0Shaffer and. 2012. The Role of Visualization in Computer Science Education. Computers in the Schools 29 1-2 (2012) 95\u2013117. arXiv:10.1080\/07380569.2012.65142210.1080\/07380569.2012.651422","DOI":"10.1080\/07380569.2012.651422"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"crossref","unstructured":"Eric Fouh Monika Akbar and Clifford\u00a0A Shaffer. 2012. The role of visualization in computer science education. Computers in the Schools 29 1-2 (2012) 95\u2013117.","DOI":"10.1080\/07380569.2012.651422"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"crossref","unstructured":"Scott Freeman Sarah\u00a0L Eddy Miles McDonough Michelle\u00a0K Smith Nnadozie Okoroafor Hannah Jordt and Mary\u00a0Pat Wenderoth. 2014. Active learning increases student performance in science engineering and mathematics. Proceedings of the national academy of sciences 111 23 (2014) 8410\u20138415.","DOI":"10.1073\/pnas.1319030111"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"crossref","unstructured":"Prakhar Ganesh Yao Chen Xin Lou Mohammad\u00a0Ali Khan Yin Yang Hassan Sajjad Preslav Nakov Deming Chen and Marianne Winslett. 2021. Compressing large-scale transformer-based models: A case study on bert. Transactions of the Association for Computational Linguistics 9 (2021) 1061\u20131080.","DOI":"10.1162\/tacl_a_00413"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Lin Gao Zekai Shao Ziqin Luo Haibo Hu Cagatay Turkay and Siming Chen. 2023. Transforlearn: Interactive visual tutorial for the transformer model. IEEE Transactions on Visualization and Computer Graphics 30 1 (2023) 891\u2013901.","DOI":"10.1109\/TVCG.2023.3327353"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","unstructured":"Gabriel Goh. 2017. Why Momentum Really Works. Distill (2017). 10.23915\/distill.00006","DOI":"10.23915\/distill.00006"},{"key":"e_1_3_3_3_31_2","volume-title":"Mechanistic Interpretability for Vision at CVPR 2025 (Non-proceedings Track)","author":"Grabe Imke","year":"2025","unstructured":"Imke Grabe, Jaden\u00a0Fiotto Kaufman, Rohit Gandikota, and David Bau. 2025. Patch Explorer: Interpreting Diffusion Models through Interaction. In Mechanistic Interpretability for Vision at CVPR 2025 (Non-proceedings Track)."},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","unstructured":"Jochen G\u00f6rtler Rebecca Kehlbeck and Oliver Deussen. 2019. A Visual Exploration of Gaussian Processes. Distill (2019). 10.23915\/distill.00017","DOI":"10.23915\/distill.00017"},{"key":"e_1_3_3_3_33_2","unstructured":"Michael Hanna Mateusz Piotrowski Jack Lindsey and Emmanuel Ameisen. 2025. circuit-tracer. https:\/\/github.com\/safety-research\/circuit-tracer. The first two authors contributed equally and are listed alphabetically.."},{"key":"e_1_3_3_3_34_2","unstructured":"Rich Harris and Svelte Contributors. 2016. Svelte: Cybernetically enhanced web apps. https:\/\/svelte.dev\/"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"crossref","unstructured":"Jeffrey Heer and George Robertson. 2007. Animated transitions in statistical data graphics. IEEE Transactions on Visualization and Computer Graphics 13 6 (2007) 1240\u20131247.","DOI":"10.1109\/TVCG.2007.70539"},{"key":"e_1_3_3_3_37_2","unstructured":"Alec Helbling and Duen\u00a0Horng Chau. 2023. ManimML: Communicating Machine Learning Architectures with Animation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.17108 (2023)."},{"key":"e_1_3_3_3_38_2","unstructured":"Evan Hernandez Arnab\u00a0Sen Sharma Tal Haklay Kevin Meng Martin Wattenberg Jacob Andreas Yonatan Belinkov and David Bau. 2023. Linearity of relation decoding in transformer language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.09124 (2023)."},{"key":"e_1_3_3_3_39_2","unstructured":"Sture Holm. 1979. A simple sequentially rejective multiple test procedure. Scand. J. Statist. 6 2 (1979) 65\u201370."},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Jooyoung Jang Christian\u00a0D Schunn and Timothy\u00a0J Nokes. 2011. Spatially distributed instructions improve learning outcomes and efficiency. Journal of educational psychology 103 1 (2011) 60.","DOI":"10.1037\/a0021994"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Theo Jaunet Corentin Kervadec Romain Vuillemot Grigory Antipov Moez Baccouche and Christian Wolf. 2021. Visqa: X-raying vision and language reasoning in transformers. IEEE Transactions on Visualization and Computer Graphics 28 1 (2021) 976\u2013986.","DOI":"10.1109\/TVCG.2021.3114683"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Minsuk Kahng Nikhil Thorat Duen Horng\u00a0(Polo) Chau Fernanda\u00a0B. Vi\u00e9gas and Martin Wattenberg. 2019. GAN Lab: Understanding Complex Deep Generative Models using Interactive Visual Experimentation. IEEE Transactions on Visualization and Computer Graphics (2019).","DOI":"10.1109\/TVCG.2018.2864500"},{"key":"e_1_3_3_3_43_2","unstructured":"Andrej Karpathy. 2016. ConvNetJS MNIST Demo. https:\/\/cs.stanford.edu\/people\/karpathy\/convnetjs\/demo\/mnist.html."},{"key":"e_1_3_3_3_44_2","unstructured":"Andrej Karpathy. 2023. nanoGPT: The simplest fastest repository for training\/finetuning medium-sized GPTs. https:\/\/github.com\/karpathy\/nanoGPT."},{"key":"e_1_3_3_3_45_2","unstructured":"Andrej Karpathy. 2024. Let\u2019s build GPT: from scratch in code spelled out. https:\/\/youtu.be\/kCc8FmEb1nY."},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","unstructured":"Colleen Kehoe John Stasko and Ashley Taylor. 2001. Rethinking the evaluation of algorithm animations as learning aids: an observational study. International Journal of Human-Computer Studies 54 2 (2001) 265\u2013284. 10.1006\/ijhc.2000.0409","DOI":"10.1006\/ijhc.2000.0409"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"crossref","unstructured":"William\u00a0H Kruskal and W\u00a0Allen Wallis. 1952. Use of ranks in one-criterion variance analysis. Journal of the American statistical Association 47 260 (1952) 583\u2013621.","DOI":"10.1080\/01621459.1952.10483441"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/VIS55277.2024.00027"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/2470654.2481287"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"crossref","unstructured":"Yiran Li Junpeng Wang Xin Dai Liang Wang Chin-Chia\u00a0Michael Yeh Yan Zheng Wei Zhang and Kwan-Liu Ma. 2023. How does attention work in vision transformers? A visual analytics attempt. IEEE Transactions on Visualization and Computer Graphics 29 6 (2023) 2888\u20132900.","DOI":"10.1109\/TVCG.2023.3261935"},{"key":"e_1_3_3_3_51_2","unstructured":"Jack Lindsey Wes Gurnee Emmanuel Ameisen Brian Chen Adam Pearce Nicholas\u00a0L. Turner Craig Citro David Abrahams Shan Carter Basil Hosmer Jonathan Marcus Michael Sklar Adly Templeton Trenton Bricken Callum McDougall Hoagy Cunningham Thomas Henighan Adam Jermyn Andy Jones Andrew Persic Zhenyi Qi T.\u00a0Ben Thompson Sam Zimmerman Kelley Rivoire Thomas Conerly Chris Olah and Joshua Batson. 2025. On the Biology of a Large Language Model. Transformer Circuits Thread (2025). https:\/\/transformer-circuits.pub\/2025\/attribution-graphs\/biology.html"},{"key":"e_1_3_3_3_52_2","series-title":"(NIPS \u201921)","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"Lu Kaiji","year":"2021","unstructured":"Kaiji Lu, Zifan Wang, Piotr Mardziel, and Anupam Datta. 2021. Influence patterns for explaining information flow in BERT. In Proceedings of the 35th International Conference on Neural Information Processing Systems(NIPS \u201921). Curran Associates Inc., Red Hook, NY, USA, Article 341, 14\u00a0pages."},{"key":"e_1_3_3_3_53_2","unstructured":"Yilin Lu Chongwei Chen Yuxin Chen Kexin Huang Marinka Zitnik and Qianwen Wang. 2024. GNN 101: Visual Learning of Graph Neural Networks in Your Web Browser. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.17849 (2024)."},{"key":"e_1_3_3_3_54_2","unstructured":"Jie Ma Yalong Bai Bineng Zhong Wei Zhang Ting Yao and Tao Mei. 2023. Visualizing and understanding patch interactions in vision transformer. IEEE Transactions on Neural Networks and Learning Systems (2023)."},{"key":"e_1_3_3_3_55_2","unstructured":"Ben Mann N Ryder M Subbiah J Kaplan P Dhariwal A Neelakantan P Shyam G Sastry A Askell S Agarwal et\u00a0al. 2020. Language models are few-shot learners. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.14165 1 (2020) 3."},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"crossref","unstructured":"Aditi Mishra Bretho Danzy Utkarsh Soni Anjana Arunkumar Jinbin Huang Bum\u00a0Chul Kwon and Chris Bryan. 2025. PromptAid: Visual prompt exploration perturbation testing and iteration for large language models. IEEE Transactions on Visualization and Computer Graphics (2025).","DOI":"10.1109\/TVCG.2025.3535332"},{"key":"e_1_3_3_3_57_2","unstructured":"MIT RAISE Initiative and Personal Robots Group MIT Media Lab. 2025. RAISE Playground. https:\/\/playground.raise.mit.edu\/"},{"key":"e_1_3_3_3_58_2","unstructured":"Evelyn Navarrete Andreas Nehring Sascha Schanze Ralph Ewerth and Anett Hoppe. 2025. A closer look into recent video-based learning research: A comprehensive review of video characteristics tools technologies and learning effectiveness. International Journal of Artificial Intelligence in Education (2025) 1\u201364."},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","unstructured":"Zhaoyang Niu Guoqiang Zhong and Hui Yu. 2021. A review on the attention mechanism of deep learning. Neurocomputing 452 (2021) 48\u201362. 10.1016\/j.neucom.2021.03.091","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"e_1_3_3_3_60_2","unstructured":"nostalgebraist. 2020. Interpreting GPT: The Logit Lens. https:\/\/www.lesswrong.com\/posts\/AcKRB8wDpdaN6v6ru\/interpreting-gpt-the-logit-lens."},{"key":"e_1_3_3_3_61_2","unstructured":"Chris Olah. 2014. Neural Networks Manifolds and Topology. https:\/\/colah.github.io\/posts\/2014-03-NN-Manifolds-Topology\/."},{"key":"e_1_3_3_3_62_2","unstructured":"Koyena Pal Jiuding Sun Andrew Yuan Byron\u00a0C Wallace and David Bau. 2023. Future lens: Anticipating subsequent tokens from a single hidden state. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.04897 (2023)."},{"key":"e_1_3_3_3_63_2","unstructured":"R2D3. [n. d.]. A Visual Introduction to Machine Learning. http:\/\/www.r2d3.us\/visual-intro-to-machine-learning-part-1\/."},{"key":"e_1_3_3_3_64_2","first-page":"8748","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748\u20138763."},{"key":"e_1_3_3_3_65_2","first-page":"28492","volume-title":"International conference on machine learning","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. 2023. Robust speech recognition via large-scale weak supervision. In International conference on machine learning. PMLR, 28492\u201328518."},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFVIS.2005.1532152"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","unstructured":"Anna Rogers Olga Kovaleva and Anna Rumshisky. 2020. A Primer in BERTology: What We Know About How BERT Works. Transactions of the Association for Computational Linguistics 8 (2020) 842\u2013866. 10.1162\/tacl_a_00349","DOI":"10.1162\/tacl_a_00349"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"crossref","unstructured":"Leonid Rozenblit and Frank Keil. 2002. The misunderstood limits of folk science: An illusion of explanatory depth. Cognitive science 26 5 (2002) 521\u2013562.","DOI":"10.1207\/s15516709cog2605_1"},{"key":"e_1_3_3_3_69_2","unstructured":"Charlie\u00a0F Ruan Yucheng Qin Xun Zhou Ruihang Lai Hongyi Jin Yixin Dong Bohan Hou Meng-Shiun Yu Yiyan Zhai Sudeep Agarwal et\u00a0al. 2024. WebLLM: A High-Performance In-Browser LLM Inference Engine. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15803 (2024)."},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"crossref","unstructured":"Zekai Shao Shuran Sun Yuheng Zhao Siyuan Wang Zhongyu Wei Tao Gui Cagatay Turkay and Siming Chen. 2023. Visual explanation for open-domain question answering with bert. IEEE Transactions on Visualization and Computer Graphics 30 7 (2023) 3779\u20133797.","DOI":"10.1109\/TVCG.2023.3243676"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSSE.2008.1443"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"crossref","unstructured":"Samuel\u00a0Sanford Shapiro and Martin\u00a0B Wilk. 1965. An analysis of variance test for normality (complete samples). Biometrika 52 3-4 (1965) 591\u2013611.","DOI":"10.1093\/biomet\/52.3-4.591"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","unstructured":"Alexander Skulmowski and M. Xu. 2022. Understanding Cognitive Load in Digital and Online Learning: a New Perspective on Extraneous Cognitive Load. Educational Psychology Review 34 1 (March 2022) 171\u2013196. 10.1007\/s10648-021-09624-7","DOI":"10.1007\/s10648-021-09624-7"},{"key":"e_1_3_3_3_74_2","unstructured":"Daniel Smilkov Shan Carter D. Sculley Fernanda\u00a0B. Vi\u00e9gas and Martin Wattenberg. 2017. Direct-Manipulation Visualization of Deep Networks. CoRR abs\/1708.03788 (2017). arXiv:https:\/\/arXiv.org\/abs\/1708.03788http:\/\/arxiv.org\/abs\/1708.03788"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","unstructured":"Hyuksoon\u00a0S. Song Martin Pusic Michael\u00a0W. Nick Umut Sarpel Jan\u00a0L. Plass and Adina\u00a0L. Kalet. 2014. The cognitive impact of interactive design features for learning complex materials in medical education. Comput. Educ. 71 (Feb. 2014) 198\u2013205. 10.1016\/j.compedu.2013.09.017","DOI":"10.1016\/j.compedu.2013.09.017"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-34738-2_6"},{"key":"e_1_3_3_3_77_2","unstructured":"Petra Ten\u00a0Hove and Hans van\u00a0der Meij. 2015. Like it or not. What characterizes YouTube\u2019s more popular instructional videos? Technical communication 62 1 (2015) 48\u201362."},{"key":"e_1_3_3_3_78_2","volume-title":"Designing interfaces: Patterns for effective interaction design","author":"Tidwell Jenifer","year":"2010","unstructured":"Jenifer Tidwell. 2010. Designing interfaces: Patterns for effective interaction design. \" O\u2019Reilly Media, Inc.\"."},{"key":"e_1_3_3_3_79_2","unstructured":"Michael Tschannen Alexey Gritsenko Xiao Wang Muhammad\u00a0Ferjad Naeem Ibrahim Alabdulmohsin Nikhil Parthasarathy Talfan Evans Lucas Beyer Ye Xia Basil Mustafa et\u00a0al. 2025. Siglip 2: Multilingual vision-language encoders with improved semantic understanding localization and dense features. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.14786 (2025)."},{"key":"e_1_3_3_3_80_2","volume-title":"The visual display of quantitative information","author":"Tufte Edward\u00a0R","year":"1983","unstructured":"Edward\u00a0R Tufte and Peter\u00a0R Graves-Morris. 1983. The visual display of quantitative information. Vol.\u00a02. Graphics press Cheshire, CT."},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"crossref","unstructured":"Barbara Tversky Julie\u00a0Bauer Morrison and Mireille Betrancourt. 2002. Animation: can it facilitate? International journal of human-computer studies 57 4 (2002) 247\u2013262.","DOI":"10.1006\/ijhc.2002.1017"},{"key":"e_1_3_3_3_82_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need(NIPS\u201917). Curran Associates Inc. 6000\u20136010."},{"key":"e_1_3_3_3_83_2","unstructured":"Bret Victor. 2011. Explorable Explanations. https:\/\/worrydream.com\/ExplorableExplanations\/."},{"key":"e_1_3_3_3_84_2","volume-title":"ICLR workshop: Debugging machine learning models","author":"Vig Jesse","year":"2019","unstructured":"Jesse Vig. 2019. BertViz: A tool for visualizing multihead self-attention in the BERT model. In ICLR workshop: Debugging machine learning models , Vol.\u00a03."},{"key":"e_1_3_3_3_85_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-demo.16"},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","unstructured":"Zijie\u00a0J. Wang Robert Turko Omar Shaikh Haekyu Park Nilaksh Das Fred Hohman Minsuk Kahng and Duen\u00a0Horng Chau. 2021. CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization. IEEE Transactions on Visualization and Computer Graphics (2021). 10.1109\/TVCG.2020.3030418","DOI":"10.1109\/TVCG.2020.3030418"},{"key":"e_1_3_3_3_87_2","doi-asserted-by":"crossref","unstructured":"Wesley Willett Jeffrey Heer and Maneesh Agrawala. 2007. Scented widgets: Improving navigation cues with embedded visualizations. IEEE Transactions on Visualization and Computer Graphics 13 6 (2007) 1129\u20131136.","DOI":"10.1109\/TVCG.2007.70589"},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_3_3_89_2","unstructured":"Mengwei Xu Wangsong Yin Dongqi Cai Rongjie Yi Daliang Xu Qipeng Wang Bingyang Wu Yihao Zhao Chen Yang Shihe Wang et\u00a0al. 2024. A survey of resource-efficient llm and multimodal foundation models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.08092 (2024)."},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","unstructured":"Catherine Yeh Yida Chen Aoyu Wu Cynthia Chen Fernanda Vi\u00e9gas and Martin Wattenberg. 2024. Attentionviz: A global view of transformer attention. IEEE Transactions on Visualization and Computer Graphics (2024). 10.1109\/TVCG.2023.3327163","DOI":"10.1109\/TVCG.2023.3327163"},{"key":"e_1_3_3_3_91_2","doi-asserted-by":"publisher","unstructured":"Yuzhe You Jarvis Tse and Jian Zhao. 2025. Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization. ACM Transactions on Interactive Intelligent Systems (2025). arxiv:https:\/\/arXiv.org\/abs\/2311.13656\u00a0[cs.HC] 10.1145\/3725739","DOI":"10.1145\/3725739"},{"key":"e_1_3_3_3_92_2","unstructured":"Zeping Yu and Sophia Ananiadou. 2023. Neuron-level knowledge attribution in large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.12141 (2023)."},{"key":"e_1_3_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"}],"event":{"name":"CHI 2026: CHI Conference on Human Factors in Computing Systems","location":"Barcelona Spain","acronym":"CHI '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772318.3791725","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T10:13:50Z","timestamp":1776248030000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772318.3791725"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":92,"alternative-id":["10.1145\/3772318.3791725","10.1145\/3772318"],"URL":"https:\/\/doi.org\/10.1145\/3772318.3791725","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}