{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:30:27Z","timestamp":1773520227080,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,2,18]]},"DOI":"10.1145\/3770761.3777298","type":"proceedings-article","created":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T15:18:26Z","timestamp":1770995906000},"page":"1345-1346","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Situating LLMs in Time: A Visual Tool for Teaching the History and Architecture of Modern NLP"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0320-7643","authenticated-orcid":false,"given":"Michael","family":"Gathara","sequence":"first","affiliation":[{"name":"University of Alabama at Brimingham, Birmingham, AL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9162-7272","authenticated-orcid":false,"given":"Aditya","family":"Makineni","sequence":"additional","affiliation":[{"name":"University of Alabama at Brimingham, Brimingham, AL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6454-6713","authenticated-orcid":false,"given":"Amber","family":"Wagner","sequence":"additional","affiliation":[{"name":"University of Alabama at Brimingham, Birmimgham, AL, USA"}]}],"member":"320","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","unstructured":"Jay Alammar. 2018. The Illustrated Transformer. https:\/\/jalammar.github.io\/illustrated-transformer\/."},{"key":"e_1_3_2_1_3_1","unstructured":"Rohan Anil Andrew M Dai Orhan Firat Melvin Johnson Dmitry Lepikhin Alexandre Passos Siamak Shakeri Emanuel Taropa Paige Bailey Zhifeng Chen et al. 2023. Palm 2 technical report. arXiv preprint arXiv:2305.10403 (2023)."},{"key":"e_1_3_2_1_4_1","unstructured":"Anthropic. 2024. The Claude 3 Model Family. (2024). https:\/\/www-cdn.anthropic. com\/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627\/Model_Card_Claude_3.pdf"},{"key":"e_1_3_2_1_5_1","volume-title":"Multimodal machine learning: A survey and taxonomy","author":"Baltru\u0161aitis Tadas","year":"2018","unstructured":"Tadas Baltru\u0161aitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multimodal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence 41, 2 (2018), 423-443."},{"key":"e_1_3_2_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877-1901."},{"key":"e_1_3_2_1_7_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24, 240 (2023), 1-113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_8_1","unstructured":"Gheorghe Comanici Eric Bieber Mike Schaekermann Ice Pasupat Noveen Sachdeva Inderjit Dhillon Marcel Blistein Ori Ram Dan Zhang Evan Rosen et al. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning multimodality long context and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)."},{"key":"e_1_3_2_1_9_1","first-page":"4171","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers). 4171-4186."},{"key":"e_1_3_2_1_10_1","unstructured":"Google. 2016. TensorFlow Playground. https:\/\/playground.tensorflow.org."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Chris Olah et al. 2018. The Building Blocks of Interpretability. Distill (2018). doi:10.23915\/distill.00010","DOI":"10.23915\/distill.00010"},{"key":"e_1_3_2_1_12_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_13_1","unstructured":"Alec Radford JeffreyWu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_2_1_14_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21, 140 (2020), 1-67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_15_1","volume-title":"The Annotated Transformer. https:\/\/nlp.seas.harvard.edu\/annotated-transformer\/. Harvard NLP Blog","author":"Rush Alexander M.","year":"2018","unstructured":"Alexander M. Rush. 2018. The Annotated Transformer. https:\/\/nlp.seas.harvard.edu\/annotated-transformer\/. Harvard NLP Blog (2018)."},{"key":"e_1_3_2_1_16_1","volume-title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=B1ckMDqlg","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, *Azalia Mirhoseini, *Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=B1ckMDqlg"},{"key":"e_1_3_2_1_17_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."}],"event":{"name":"SIGCSE TS 2026:The 57th ACM Technical Symposium on Computer Science Education","location":"St. Louis MO USA","sponsor":["SIGCSE ACM Special Interest Group on Computer Science Education"]},"container-title":["Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770761.3777298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:19:41Z","timestamp":1773508781000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770761.3777298"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,17]]},"references-count":19,"alternative-id":["10.1145\/3770761.3777298","10.1145\/3770761"],"URL":"https:\/\/doi.org\/10.1145\/3770761.3777298","relation":{},"subject":[],"published":{"date-parts":[[2026,2,17]]},"assertion":[{"value":"2026-02-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}