{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:46:42Z","timestamp":1783738002369,"version":"3.55.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031984136","type":"print"},{"value":"9783031984143","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\/978-3-031-98414-3_23","type":"book-chapter","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T02:14:38Z","timestamp":1752804878000},"page":"323-337","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Beyond Final Answers: Evaluating Large Language Models for\u00a0Math Tutoring"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1218-0630","authenticated-orcid":false,"given":"Adit","family":"Gupta","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6731-9401","authenticated-orcid":false,"given":"Jennifer","family":"Reddig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3200-2348","authenticated-orcid":false,"given":"Tommaso","family":"Cal\u00f2","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0079-8000","authenticated-orcid":false,"given":"Daniel","family":"Weitekamp","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3084-5189","authenticated-orcid":false,"given":"Christopher\u00a0J.","family":"MacLellan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"23_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1007\/11774303_7","volume-title":"Intelligent Tutoring Systems","author":"V Aleven","year":"2006","unstructured":"Aleven, V., McLaren, B.M., Sewall, J., Koedinger, K.R.: The cognitive tutor authoring tools (CTAT): preliminary evaluation of efficiency gains. In: Ikeda, M., Ashley, K.D., Chan, T.-W. (eds.) ITS 2006. LNCS, vol. 4053, pp. 61\u201370. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11774303_7"},{"issue":"6","key":"23_CR2","doi-asserted-by":"publisher","first-page":"4","DOI":"10.3102\/0013189X013006004","volume":"13","author":"BS Bloom","year":"1984","unstructured":"Bloom, B.S.: The 2 sigma problem: the search for methods of group instruction as effective as one-to-one tutoring. Educ. Res. 13(6), 4\u201316 (1984)","journal-title":"Educ. Res."},{"issue":"2","key":"23_CR3","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1191\/1478088706qp063oa","volume":"3","author":"V Braun","year":"2006","unstructured":"Braun, V., Clarke, V.: Using thematic analysis in psychology. Qual. Res. Psychol. 3(2), 77\u2013101 (2006)","journal-title":"Qual. Res. Psychol."},{"issue":"7\u20138","key":"23_CR4","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1080\/08832323.2024.2432936","volume":"99","author":"CC Cicchetti","year":"2024","unstructured":"Cicchetti, C.C.: AI in higher education: does not help, might hurt. J. Educ. Bus. 99(7\u20138), 438\u2013443 (2024)","journal-title":"J. Educ. Bus."},{"key":"23_CR5","unstructured":"Cobbe, K., Kosaraju, V., Bavarian, M., Chen, J.H., Raffel, C., Schulman, J.: Training verifiers to solve math word problems. arXiv:2110.14168 (2021)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Corbett, A.T., Anderson, J.R.: Knowledge tracing: modeling the acquisition of procedural knowledge. User Model. User-Adapted Interact. (1994)","DOI":"10.1007\/BF01099821"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Fang, M., Wan, X., Lu, F., Xing, F., Zou, K.: MathOdyssey: benchmarking mathematical problem-solving skills in large language models using odyssey math data. arXiv:2406.18321 (2024)","DOI":"10.1038\/s41597-025-05283-3"},{"key":"23_CR8","unstructured":"Gupta, A., Siddiqui, M., Smith, G., Reddig, J., MacLellan, C.: Intelligent tutors for adult learners: an analysis of needs and challenges. arXiv:2412.04477 (2025)"},{"key":"23_CR9","doi-asserted-by":"publisher","first-page":"470","DOI":"10.1007\/s40593-014-0024-x","volume":"24","author":"N Heffernan","year":"2014","unstructured":"Heffernan, N., Heffernan, C.: The ASSISTments ecosystem: building a platform that brings scientists and teachers together for minimally invasive research on human learning and teaching. Int. J. Artif. Intell. Educ. 24, 470\u2013497 (2014)","journal-title":"Int. J. Artif. Intell. Educ."},{"issue":"2","key":"23_CR10","doi-asserted-by":"publisher","first-page":"153","DOI":"10.3233\/IRG-2008-18(2)04","volume":"18","author":"NT Heffernan","year":"2008","unstructured":"Heffernan, N.T., Koedinger, K.R., Razzaq, L.: Expanding the model-tracing architecture: a 3rd generation intelligent tutor for algebra symbolization. Int. J. Artif. Intell. Educ. 18(2), 153\u2013178 (2008)","journal-title":"Int. J. Artif. Intell. Educ."},{"key":"23_CR11","unstructured":"Hendrycks, D., et al.: Measuring mathematical problem solving with the MATH dataset. arXiv:2103.03874 (2021)"},{"key":"23_CR12","unstructured":"Huang, L., et al.: A survey on hallucination in large language models: principles, taxonomy, challenges, and open questions. arXiv:2311.05232 (2023)"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Kestin, G., Miller, K., Klales, A., et\u00a0al.: AI tutoring outperforms active learning. Res. Square (2024). https:\/\/doi.org\/10.21203\/rs.3.rs-4243877\/v1","DOI":"10.21203\/rs.3.rs-4243877\/v1"},{"key":"23_CR14","unstructured":"Khan, S.: Sal Khan explores ChatGPT in education. YouTube video. Published on Khan Academy\u2019s Official Channel, March 2023"},{"key":"23_CR15","unstructured":"Kim, J.S.: Jamplate: exploring LLM-enhanced templates for idea reflection. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems, New York, NY, USA, pp. 1\u201314 (2023)"},{"key":"23_CR16","unstructured":"Koedinger, K.R., Anderson, J.R., Hadley, W.H., Mark, M.A.: Intelligent tutoring goes to school in the big city. Int. J. Artif. Intell. Educ. 8, 30\u201343 (1997). ffhal-00197383"},{"issue":"1","key":"23_CR17","doi-asserted-by":"publisher","first-page":"42","DOI":"10.3102\/0034654315581420","volume":"86","author":"JA Kulik","year":"2016","unstructured":"Kulik, J.A., Fletcher, J.: Effectiveness of intelligent tutoring systems: a meta-analytic review. Rev. Educ. Res. 86(1), 42\u201378 (2016)","journal-title":"Rev. Educ. Res."},{"key":"23_CR18","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/3-540-68716-5_29","volume-title":"Intelligent Tutoring Systems","author":"MC Lovett","year":"1998","unstructured":"Lovett, M.C.: Cognitive task analysis in service of intelligent tutoring systems design: a case study in statistics. In: Goettl, B.P., Halff, H.M., Redfield, C.L., Shute, V.J. (eds.) Intelligent Tutoring Systems. LNCS, vol. 1452, pp. 234\u2013243. Springer, New York (1998)"},{"issue":"3","key":"23_CR19","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","volume":"22","author":"ML McHugh","year":"2012","unstructured":"McHugh, M.L.: Interrater reliability: the Kappa statistic. Biochemia Medica 22(3), 276\u2013282 (2012)","journal-title":"Biochemia Medica"},{"key":"23_CR20","unstructured":"Mirzadeh, I., Alizadeh, K., Shahrokhi, H., Tuzel, O., Bengio, S., Farajtabar, M.: GSM-symbolic: understanding the limitations of mathematical reasoning in large language models. arXiv:2410.05229 (2024)"},{"issue":"4","key":"23_CR21","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/BF00168958","volume":"4","author":"HS Nwana","year":"1990","unstructured":"Nwana, H.S.: Intelligent tutoring systems: an overview. Artif. Intell. Rev. 4(4), 251\u2013277 (1990)","journal-title":"Artif. Intell. Rev."},{"key":"23_CR22","unstructured":"OpenAI. GPT-4 technical report. arXiv:2303.08774 (2023)"},{"key":"23_CR23","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-031-63028-6_11","volume-title":"Artificial Intelligence in Education","author":"JW Park","year":"2023","unstructured":"Park, J.W., Kim, M.J., Lee, S.W.: Developing conversational intelligent tutoring for speaking skills in foreign language education. In: Koch, F., Zhang, L., Chen, F., Dillenbourg, P. (eds.) Artificial Intelligence in Education, pp. 123\u2013134. Springer International Publishing, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-63028-6_11"},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Reddig, J.M., Arora, A., MacLellan, C.: Generating in-context, personalized feedback for intelligent tutors with large language models (2024)","DOI":"10.1007\/s40593-025-00505-6"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"VanLehn, K.: The behavior of tutoring systems. Int. J. Artif. Intell. Educ., 227\u2013265 (2006)","DOI":"10.3233\/IRG-2006-16(3)02"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"VanLehn, K.: The relative effectiveness of human tutoring, intelligent tutoring systems, and other tutoring systems. Educ. Psychol. (2011)","DOI":"10.1080\/00461520.2011.611369"},{"key":"23_CR27","unstructured":"Xia, S., et al.: Evaluating mathematical reasoning beyond accuracy. arXiv:2404.05692 (2024)"},{"key":"23_CR28","unstructured":"Zhang, Y., et al.: Workedgen: using LLMs to generate interactive worked programming examples. In: Proceedings of the 2023 Conference on Learning at Scale, pp. 123\u2013134 (2023)"}],"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\/978-3-031-98414-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:44:20Z","timestamp":1780375460000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-98414-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031984136","9783031984143"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-98414-3_23","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":"15 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"}}]}}