{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T20:04:22Z","timestamp":1766088262834,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031642982"},{"type":"electronic","value":"9783031642999"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-64299-9_4","type":"book-chapter","created":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T09:02:00Z","timestamp":1719824520000},"page":"47-61","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluating Behaviors of\u00a0General Purpose Language Models in\u00a0a\u00a0Pedagogical Context"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7920-4510","authenticated-orcid":false,"given":"Shamya","family":"Karumbaiah","sequence":"first","affiliation":[]},{"given":"Ananya","family":"Ganesh","sequence":"additional","affiliation":[]},{"given":"Aayush","family":"Bharadwaj","sequence":"additional","affiliation":[]},{"given":"Lucas","family":"Anderson","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,2]]},"reference":[{"issue":"1","key":"4_CR1","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1002\/tea.20446","volume":"49","author":"LK Berland","year":"2012","unstructured":"Berland, L.K., Hammer, D.: Framing for scientific argumentation. J. Res. Sci. Teach. 49(1), 68\u201394 (2012)","journal-title":"J. Res. Sci. Teach."},{"key":"4_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compedu.2021.104351","volume":"176","author":"L Gerard","year":"2022","unstructured":"Gerard, L., Linn, M.C., Berkeley, U.C.: Computer-based guidance to support students\u2019 revision of their science explanations. Comput. Educ. 176, 104351 (2022)","journal-title":"Comput. Educ."},{"key":"4_CR3","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding (2020)"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Jacovi, A., Marasovi\u0107, A., Miller, T., Goldberg, Y.: Formalizing trust in artificial intelligence: prerequisites, causes and goals of human trust in AI. In: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, pp. 624\u2013635 (2021)","DOI":"10.1145\/3442188.3445923"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Karumbaiah, S., Lan, A., Nagpal, S., Baker, R.S., Botelho, A., Heffernan, N.: Using past data to warm start active machine learning: does context matter? In: LAK21: 11th International Learning Analytics and Knowledge Conference, pp. 151\u2013160 (2021)","DOI":"10.1145\/3448139.3448154"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Kimble, G.A.: The scientific value of undergraduate research participation (1987)","DOI":"10.1037\/\/0003-066X.42.3.267.b"},{"issue":"9","key":"4_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3560815","volume":"55","author":"P Liu","year":"2023","unstructured":"Liu, P., Yuan, W., Jinlan, F., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9), 1\u201335 (2023)","journal-title":"ACM Comput. Surv."},{"key":"4_CR8","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"4_CR9","unstructured":"Longpre, S., et\u00a0al. The flan collection: designing data and methods for effective instruction tuning. arXiv preprint arXiv:2301.13688 (2023)"},{"issue":"12","key":"4_CR10","doi-asserted-by":"publisher","first-page":"2026","DOI":"10.1080\/09500693.2016.1221547","volume":"38","author":"KL McNeill","year":"2016","unstructured":"McNeill, K.L., Katsh-Singer, R., Gonz\u00e1lez-Howard, M., Loper, S.: Factors impacting teachers\u2019 argumentation instruction in their science classrooms. Int. J. Sci. Educ. 38(12), 2026\u20132046 (2016)","journal-title":"Int. J. Sci. Educ."},{"key":"4_CR11","unstructured":"Nardo, C.: The waluigi effect (mega-post). Less Wrong (2023)"},{"key":"4_CR12","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262170055.001.0001","volume-title":"Dataset Shift in Machine Learning","author":"J Quinonero-Candela","year":"2008","unstructured":"Quinonero-Candela, J., Sugiyama, M., Schwaighofer, A., Lawrence, N.D.: Dataset Shift in Machine Learning. MIT Press, Cambridge (2008)"},{"key":"4_CR13","unstructured":"Recht, B., Roelofs, R., Schmidt, L., Shankar, V.: Do imagenet classifiers generalize to imagenet? In: International Conference on Machine Learning, pp. 5389\u20135400. PMLR (2019)"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T., Lundberg, S.: Adaptive testing and debugging of NLP models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers), pp. 3253\u20133267 (2022)","DOI":"10.18653\/v1\/2022.acl-long.230"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Ribeiro, M.T, Wu, T., Guestrin, C., Singh, S.: Beyond accuracy: behavioral testing of NLP models with checklist. arXiv preprint arXiv:2005.04118 (2020)","DOI":"10.24963\/ijcai.2021\/659"},{"issue":"1","key":"4_CR16","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41746-020-0253-3","volume":"3","author":"MP Sendak","year":"2020","unstructured":"Sendak, M.P., Gao, M., Brajer, N., Balu, S.: Presenting machine learning model information to clinical end users with model facts labels. NPJ Dig. Med. 3(1), 41 (2020)","journal-title":"NPJ Dig. Med."},{"key":"4_CR17","unstructured":"Next Generation Science Standards\u00a0Lead States. Next generation science standards: For states, by states. Appendix D: All standards, all students: Making the Next Generation Science Standards accessible to all students (2013)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Suresh, H., et al.: Kaleidoscope: semantically-grounded, context-specific ml model evaluation. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, pp. 1\u201313 (2023)","DOI":"10.1145\/3544548.3581482"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: Glue: a multi-task benchmark and analysis platform for natural language understanding (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"4_CR20","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1162\/tacl_a_00290","volume":"7","author":"A Warstadt","year":"2019","unstructured":"Warstadt, A., Singh, A., Bowman, S.R.: Neural network acceptability judgments. Trans. Assoc. Comput. Linguist. 7, 625\u2013641 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"4_CR21","unstructured":"Wolf, T., et\u00a0al.: Huggingface\u2019s transformers: state-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Wu, T., Ribeiro, M.T., Heer, J., Weld, D.S.: Errudite: scalable, reproducible, and testable error analysis. In: Annual Meeting of the Association for Computational Linguistics, pp. 747\u2013763 (2019)","DOI":"10.18653\/v1\/P19-1073"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-64299-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,1]],"date-time":"2024-07-01T09:05:55Z","timestamp":1719824755000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-64299-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031642982","9783031642999"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-64299-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"2 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIED","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Intelligence in Education","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Recife","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aied2024.cesar.school\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}