{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T21:30:21Z","timestamp":1777152621064,"version":"3.51.4"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031984648","type":"print"},{"value":"9783031984655","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-98465-5_51","type":"book-chapter","created":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T01:46:53Z","timestamp":1752889613000},"page":"405-412","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Turing-Like Test for\u00a0Personalized Educational AI"],"prefix":"10.1007","author":[{"given":"Shashank","family":"Sonkar","sequence":"first","affiliation":[]},{"given":"Naiming","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xinghe","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Baraniuk","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"51_CR1","unstructured":"Biderman, S., et al.: Lessons from the trenches on reproducible evaluation of language models (2024). https:\/\/arxiv.org\/abs\/2405.14782"},{"key":"51_CR2","unstructured":"Chowdhury, S.P., Zouhar, V., Sachan, M.: Autotutor meets large language models: a language model tutor with rich pedagogy and guardrails (2024). https:\/\/arxiv.org\/abs\/2402.09216"},{"key":"51_CR3","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/BF01099821","volume":"4","author":"AT Corbett","year":"1994","unstructured":"Corbett, A.T., Anderson, J.R.: Knowledge tracing: modeling the acquisition of procedural knowledge. User Model. User-Adap. Inter. 4, 253\u2013278 (1994)","journal-title":"User Model. User-Adap. Inter."},{"key":"51_CR4","unstructured":"Feng, K., Ding, K., Ma, K., Wang, Z., Zhang, Q., Chen, H.: Sample-efficient human evaluation of large language models via maximum discrepancy competition (2024). https:\/\/arxiv.org\/abs\/2404.08008"},{"key":"51_CR5","unstructured":"King, J., et al.: Eedi - mining misconceptions in mathematics. https:\/\/kaggle.com\/competitions\/eedi-mining-misconceptions-in-mathematics (2024), kaggle"},{"key":"51_CR6","unstructured":"Klymkowsky, M., Cooper, M.M.: The end of multiple choice tests: using ai to enhance assessment (2024), https:\/\/arxiv.org\/abs\/2406.07481"},{"key":"51_CR7","unstructured":"Laskar, M.T.R., et al.: A systematic survey and critical review on evaluating large language models: challenges, limitations, and recommendations (2024). https:\/\/arxiv.org\/abs\/2407.04069"},{"key":"51_CR8","doi-asserted-by":"crossref","unstructured":"Liu, N., Sonkar, S., Le, M., Baraniuk, R.: Malalgoqa: pedagogical evaluation of counterfactual reasoning in large language models and implications for ai in education (2024). https:\/\/arxiv.org\/abs\/2407.00938","DOI":"10.18653\/v1\/2024.findings-emnlp.913"},{"key":"51_CR9","doi-asserted-by":"publisher","unstructured":"Pane, J.F., Griffin, B.A., McCaffrey, D.F., Karam, R.T.: Effectiveness of cognitive tutor algebra i at scale. Educ. Eval. Policy Anal. 36(2), 127\u2013144 (2014). https:\/\/doi.org\/10.3102\/0162373713507480, https:\/\/journals.sagepub.com\/doi\/10.3102\/0162373713507480","DOI":"10.3102\/0162373713507480"},{"key":"51_CR10","doi-asserted-by":"publisher","unstructured":"Roschelle, J., Feng, M., Murphy, R.F., Mason, C.A.: Online mathematics homework increases student achievement. AERA Open 2(4), 1\u201312 (2016). https:\/\/doi.org\/10.1177\/2332858416673968, https:\/\/journals.sagepub.com\/doi\/10.1177\/2332858416673968","DOI":"10.1177\/2332858416673968"},{"key":"51_CR11","unstructured":"Schmucker, R., Xia, M., Azaria, A., Mitchell, T.: Ruffle &riley: towards the automated induction of conversational tutoring systems. arXiv preprint arXiv:2310.01420 (2023)"},{"issue":"4","key":"51_CR12","first-page":"387","volume":"8","author":"D Sleeman","year":"1984","unstructured":"Sleeman, D.: An attempt to understand students\u2019 understanding of basic algebra. Cogn. Sci. 8(4), 387\u2013412 (1984)","journal-title":"Cogn. Sci."},{"key":"51_CR13","doi-asserted-by":"publisher","unstructured":"Sonkar, S., Chen, X., Le, M., Liu, N., Basu\u00a0Mallick, D., Baraniuk, R.: Code soliloquies for accurate calculations in large language models. In: Proceedings of the 14th Learning Analytics and Knowledge Conference: LAK 2024, pp. 828\u2013835. Association for Computing Machinery, New York (2024). https:\/\/doi.org\/10.1145\/3636555.3636889","DOI":"10.1145\/3636555.3636889"},{"key":"51_CR14","doi-asserted-by":"publisher","unstructured":"Sonkar, S., Liu, N., Baraniuk, R.: Student data paradox and curious case of single student-tutor model: Regressive side effects of training LLMs for personalized learning. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 15543\u201315553. Association for Computational Linguistics, Miami, Florid (Nov 2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.912, https:\/\/aclanthology.org\/2024.findings-emnlp.912","DOI":"10.18653\/v1\/2024.findings-emnlp.912"},{"key":"51_CR15","doi-asserted-by":"publisher","unstructured":"Sonkar, S., Liu, N., Mallick, D., Baraniuk, R.: CLASS: a design framework for building intelligent tutoring systems based on learning science principles. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 1941\u20131961. Association for Computational Linguistics, Singapore (Dec 2023). https:\/\/doi.org\/10.18653\/v1\/2023.findings-emnlp.130, https:\/\/aclanthology.org\/2023.findings-emnlp.130","DOI":"10.18653\/v1\/2023.findings-emnlp.130"},{"key":"51_CR16","doi-asserted-by":"publisher","unstructured":"Sonkar, S., Ni, K., Chaudhary, S., Baraniuk, R.: Pedagogical alignment of large language models. In: Al-Onaizan, Y., Bansal, M., Chen, Y.N. (eds.) Findings of the Association for Computational Linguistics: EMNLP 2024. pp. 13641\u201313650. Association for Computational Linguistics, Miami, Florida, USA (Nov 2024). https:\/\/doi.org\/10.18653\/v1\/2024.findings-emnlp.797, https:\/\/aclanthology.org\/2024.findings-emnlp.797","DOI":"10.18653\/v1\/2024.findings-emnlp.797"},{"key":"51_CR17","unstructured":"Zaphir, L., Lodge, J.M., Lisec, J., McGrath, D., Khosravi, H.: How critically can an ai think? a framework for evaluating the quality of thinking of generative artificial intelligence (2024). https:\/\/arxiv.org\/abs\/2406.14769"}],"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\/978-3-031-98465-5_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T14:48:47Z","timestamp":1757256527000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-98465-5_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031984648","9783031984655"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-98465-5_51","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"20 July 2025","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":"Palermo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aied2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aied2025.itd.cnr.it\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}