{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T05:12:01Z","timestamp":1780377121539,"version":"3.54.1"},"publisher-location":"Cham","reference-count":49,"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_18","type":"book-chapter","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T02:14:20Z","timestamp":1752804860000},"page":"251-266","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Training LLM-Based Tutors to\u00a0Improve Student Learning Outcomes in\u00a0Dialogues"],"prefix":"10.1007","author":[{"given":"Alexander","family":"Scarlatos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naiming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaewook","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Baraniuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"issue":"2","key":"18_CR1","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1207\/s15327809jls0402_2","volume":"4","author":"JR Anderson","year":"1995","unstructured":"Anderson, J.R., Corbett, A.T., Koedinger, K.R., Pelletier, R.: Cognitive tutors: lessons learned. J. Learn. Sci. 4(2), 167\u2013207 (1995)","journal-title":"J. Learn. Sci."},{"key":"18_CR2","unstructured":"Ashok\u00a0Kumar, N., Lan, A.: Improving socratic question generation using data augmentation and preference optimization. In: Proceedings of the 19th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2024), pp. 108\u2013118. Association for Computational Linguistics, Mexico City, Mexico, June 2024"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Cai, D., Zhang, Y., Dai, B.: Learning path recommendation based on knowledge tracing model and reinforcement learning. In: 2019 IEEE 5th International Conference on Computer and Communications (ICCC), pp. 1881\u20131885. IEEE (2019)","DOI":"10.1109\/ICCC47050.2019.9064104"},{"key":"18_CR4","unstructured":"Carnegie Learning: Livehint overview (2024). https:\/\/support.carnegielearning.com\/help-center\/math\/livehint\/article\/livehint-overview\/"},{"key":"18_CR5","unstructured":"Cobbe, K., etal.: Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)"},{"key":"18_CR6","unstructured":"Common Core State Standards Initiative: Mathematics standards (2024). https:\/\/www.thecorestandards.org\/Math\/"},{"issue":"4","key":"18_CR7","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/BF01099821","volume":"4","author":"A Corbett","year":"1994","unstructured":"Corbett, A., Anderson, J.: Knowledge tracing: modeling the acquisition of procedural knowledge. User Model. User-adapted Interact. 4(4), 253\u2013278 (1994)","journal-title":"User Model. User-adapted Interact."},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Cui, P., Sachan, M.: Adaptive and personalized exercise generation for online language learning. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 10184\u201310198 (2023)","DOI":"10.18653\/v1\/2023.acl-long.567"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Demszky, D., et al.: Measuring conversational uptake: A case study on student-teacher interactions. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 1638\u20131653 (2021)","DOI":"10.18653\/v1\/2021.acl-long.130"},{"key":"18_CR10","unstructured":"Dubey, A., et\u00a0al.: The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"18_CR11","unstructured":"Face, H.: Hugging face - the ai community building the future. https:\/\/huggingface.co\/ (2025). Accessed 18 Feb 2025"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Fernandez, N., Scarlatos, A., Feng, W., Woodhead, S., Lan, A.: DiVERT: distractor generation with variational errors represented as text for math multiple-choice questions. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 9063\u20139081. Association for Computational Linguistics, Miami, Florida, USA, November 2024","DOI":"10.18653\/v1\/2024.emnlp-main.512"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Heffernan, N., Lan, A.S.: Context-aware attentive knowledge tracing. In: Proc. ACM SIGKDD, pp. 2330\u20132339 (2020)","DOI":"10.1145\/3394486.3403282"},{"issue":"4","key":"18_CR14","first-page":"39","volume":"22","author":"AC Graesser","year":"2001","unstructured":"Graesser, A.C., VanLehn, K., Ros\u00e9, C.P., Jordan, P.W., Harter, D.: Intelligent tutoring systems with conversational dialogue. AI Mag. 22(4), 39\u201339 (2001)","journal-title":"AI Mag."},{"key":"18_CR15","unstructured":"He-Yueya, J., Goodman, N.D., Brunskill, E.: Evaluating and optimizing educational content with large language model judgments. In: Proceedings of the 17th International Conference on Educational Data Mining, pp. 68\u201382 (2024)"},{"key":"18_CR16","unstructured":"He-Yueya, J., Singla, A.: Quizzing policy using reinforcement learning for inferring the student knowledge state. International Educational Data Mining Society (2021)"},{"key":"18_CR17","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"18_CR18","unstructured":"Jia, Q., Young, M., Xiao, Y., Cui, J., Liu, C., Rashid, P., Gehringer, E.: Insta-reviewer: a data-driven approach for generating instant feedback on students\u2019 project reports. International Educational Data Mining Society (2022)"},{"key":"18_CR19","unstructured":"Kakarla, S., Thomas, D., Lin, J., Gupta, S., Koedinger, K.: Using large language models to assess tutors\u2019 performance in reacting to students making math errors. In: AI for Education: Bridging Innovation and Responsibility at the 38th AAAI Annual Conference on AI (2024)"},{"key":"18_CR20","unstructured":"Kendall, M.G.: Rank correlation methods (1948)"},{"key":"18_CR21","unstructured":"Khan Academy: Supercharge your teaching experience with khanmigo (2023). https:\/\/www.khanmigo.ai\/"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Kim, K., Seo, A.J., Liu, H., Shin, J., Lee, K.: Margin matching preference optimization: Enhanced model alignment with granular feedback. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 13554\u201313570. Association for Computational Linguistics, Miami, Florida, USA, November 2024","DOI":"10.18653\/v1\/2024.findings-emnlp.792"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Krupp, L., etal.: Challenges and opportunities of moderating usage of large language models in education. In: Proceedings of the International Conference on Mobile and Ubiquitous Multimedia, pp. 249\u2013254 (2024)","DOI":"10.1145\/3701571.3701590"},{"issue":"1","key":"18_CR24","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1080\/00031305.1988.10475524","volume":"42","author":"J Lee Rodgers","year":"1988","unstructured":"Lee Rodgers, J., Nicewander, W.A.: Thirteen ways to look at the correlation coefficient. Am. Stat. 42(1), 59\u201366 (1988)","journal-title":"Am. Stat."},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Lieb, A., Goel, T.: Student interaction with newtbot: An llm-as-tutor chatbot for secondary physics education. In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp.\u00a01\u20138 (2024)","DOI":"10.1145\/3613905.3647957"},{"key":"18_CR26","unstructured":"Liu, N., Sonkar, S., Wang, Z., Woodhead, S., Baraniuk, R.G.: Novice learner and expert tutor: Evaluating math reasoning abilities of large language models with misconceptions. arXiv preprint arXiv:2310.02439 (2023)"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Liu, N., Wang, Z., Baraniuk, R., Lan, A.: Open-ended knowledge tracing for computer science education. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.254"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Macina, J., et al.: MathDial: a dialogue tutoring dataset with rich pedagogical properties grounded in math reasoning problems. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 5602\u20135621. Association for Computational Linguistics, Singapore (Dec 2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.372"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Nickow, A., Oreopoulos, P., Quan, V.: The impressive effects of tutoring on prek-12 learning: A systematic review and meta-analysis of the experimental evidence. Working Paper 27476, National Bureau of Economic Research, July 2020","DOI":"10.3386\/w27476"},{"key":"18_CR30","unstructured":"OpenAI: Hello gpt-4o, May 2024. https:\/\/openai.com\/index\/hello-gpt-4o\/. Accessed 19 Feb 2025"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Pal\u00a0Chowdhury, S., Zouhar, V., Sachan, M.: Autotutor meets large language models: a language model tutor with rich pedagogy and guardrails. In: Proceedings of the Eleventh ACM Conference on Learning@ Scale, pp. 5\u201315 (2024)","DOI":"10.1145\/3657604.3662041"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Park, M., Kim, S., Lee, S., Kwon, S., Kim, K.: Empowering personalized learning through a conversation-based tutoring system with student modeling. In: Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, pp. 1\u201310 (2024)","DOI":"10.1145\/3613905.3651122"},{"key":"18_CR33","unstructured":"Piech, C., Bassen, J., Huang, J., Ganguli, S., Sahami, M., Guibas, L.J., Sohl-Dickstein, J.: Deep knowledge tracing. In: Proc. NeurIPS, pp. 505\u2013513 (2015)"},{"key":"18_CR34","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: Your language model is secretly a reward model. Advances in Neural Information Processing Systems 36 (2024)"},{"issue":"6","key":"18_CR35","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1111\/cogs.12290","volume":"40","author":"AN Rafferty","year":"2016","unstructured":"Rafferty, A.N., Brunskill, E., Griffiths, T.L., Shafto, P.: Faster teaching via pomdp planning. Cogn. Sci. 40(6), 1290\u20131332 (2016)","journal-title":"Cogn. Sci."},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Scarlatos, A., Baker, R.S., Lan, A.: Exploring knowledge tracing in tutor-student dialogues using llms. In: Proceedings of the 15th Learning Analytics and Knowledge Conference, LAK 2025, Dublin, Ireland, March 3-7, 2025. ACM (2025)","DOI":"10.1145\/3706468.3706501"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Scarlatos, A., Smith, D., Woodhead, S., Lan, A.: Improving the validity of automatically generated feedback via reinforcement learning. In: International Conference on Artificial Intelligence in Education, pp. 280\u2013294. Springer (2024)","DOI":"10.1007\/978-3-031-64302-6_20"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Schmucker, R., Xia, M., Azaria, A., Mitchell, T.: Ruffle &riley: Insights from designing and evaluating a large language model-based conversational tutoring system. In: International Conference on Artificial Intelligence in Education, pp. 75\u201390. Springer (2024)","DOI":"10.1007\/978-3-031-64302-6_6"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Sonkar, S., Liu, N., Mallick, D., Baraniuk, R.: CLASS: a design framework for building intelligent tutoring systems based on learning science principles. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 1941\u20131961. Association for Computational Linguistics, Singapore, December 2023","DOI":"10.18653\/v1\/2023.findings-emnlp.130"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Sonkar, S., Ni, K., Chaudhary, S., Baraniuk, R.: Pedagogical alignment of large language models. In: Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 13641\u201313650. Association for Computational Linguistics, Miami, Florida, USA, November 2024","DOI":"10.18653\/v1\/2024.findings-emnlp.797"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Stamper, J., Xiao, R., Hou, X.: Enhancing llm-based feedback: Insights from intelligent tutoring systems and the learning sciences. In: International Conference on Artificial Intelligence in Education, pp. 32\u201343. Springer (2024)","DOI":"10.1007\/978-3-031-64315-6_3"},{"key":"18_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.learninstruc.2024.101894","volume":"91","author":"J Steiss","year":"2024","unstructured":"Steiss, J., et al.: Comparing the quality of human and chatgpt feedback of students\u2019 writing. Learn. Instr. 91, 101894 (2024)","journal-title":"Learn. Instr."},{"key":"18_CR43","unstructured":"Team, L.: Learnlm: Improving gemini for learning (2024)"},{"key":"18_CR44","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1007\/3-540-47987-2_20","volume-title":"Intelligent Tutoring Systems","author":"K VanLehn","year":"2002","unstructured":"VanLehn, K., et al.: The architecture of why2-Atlas: a coach for qualitative physics essay writing. In: Cerri, S.A., Gouard\u00e8res, G., Paragua\u00e7u, F. (eds.) ITS 2002. LNCS, vol. 2363, pp. 158\u2013167. Springer, Heidelberg (2002). https:\/\/doi.org\/10.1007\/3-540-47987-2_20"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Wang, R., Zhang, Q., Robinson, C., Loeb, S., Demszky, D.: Bridging the novice-expert gap via models of decision-making: A case study on remediating math mistakes. In: Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pp. 2174\u20132199 (2024)","DOI":"10.18653\/v1\/2024.naacl-long.120"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Wang, R.E., Ribeiro, A.T., Robinson, C.D., Loeb, S., Demszky, D.: Tutor copilot: A human-ai approach for scaling real-time expertise. arXiv preprint arXiv:2410.03017 (2024)","DOI":"10.21203\/rs.3.rs-5363154\/v1"},{"key":"18_CR47","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Cref: an llm-based conversational software repair framework for programming tutors. In: Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, pp. 882\u2013894 (2024)","DOI":"10.1145\/3650212.3680328"},{"key":"18_CR48","volume-title":"Survey on knowledge distillation for large language models: Methods, evaluation, and application","author":"C Yang","year":"2024","unstructured":"Yang, C., et al.: Survey on knowledge distillation for large language models: Methods, evaluation, and application. ACM Trans. Intell. Syst, Technol (2024)"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xie, J., Wu, C., Cai, J., Kim, C., Carroll, J.M.: The future of learning: Large language models through the lens of students. In: Proceedings of the 25th Annual Conference on Information Technology Education, pp. 12\u201318 (2024)","DOI":"10.1145\/3686852.3687069"}],"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_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:47:52Z","timestamp":1780375672000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-98414-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031984136","9783031984143"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-98414-3_18","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"}}]}}