{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:46:32Z","timestamp":1772909192730,"version":"3.50.1"},"reference-count":56,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T00:00:00Z","timestamp":1720483200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T00:00:00Z","timestamp":1720483200000},"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":["Int J Artif Intell Educ"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s40593-024-00416-y","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T13:08:46Z","timestamp":1720530526000},"page":"509-532","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Math-LLMs: AI Cyberinfrastructure with Pre-trained Transformers for Math Education"],"prefix":"10.1016","volume":"35","author":[{"given":"Fan","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Chenglu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Owen","family":"Henkel","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1446-889X","authenticated-orcid":false,"given":"Wanli","family":"Xing","sequence":"additional","affiliation":[]},{"given":"Sami","family":"Baral","sequence":"additional","affiliation":[]},{"given":"Neil","family":"Heffernan","sequence":"additional","affiliation":[]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[]}],"member":"78","published-online":{"date-parts":[[2024,7,9]]},"reference":[{"key":"416_CR1","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11409-013-9107-6","volume":"9","author":"M Bannert","year":"2014","unstructured":"Bannert, M., Reimann, P., & Sonnenberg, C. (2014). Process mining techniques for analysing patterns and strategies in students\u2019 self-regulated learning. Metacognition and Learning, 9, 161\u2013185.","journal-title":"Metacognition and Learning"},{"issue":"6","key":"416_CR2","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1080\/09500782.2020.1842443","volume":"35","author":"GC Bunch","year":"2021","unstructured":"Bunch, G. C., & Martin, D. (2021). From \u201cacademic language\u201d to the \u201clanguage of ideas\u201d: A disciplinary perspective on using language in k-12 settings. Language and Education, 35(6), 539\u2013556.","journal-title":"Language and Education"},{"key":"416_CR3","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/s11409-015-9142-6","volume":"11","author":"AA Callender","year":"2016","unstructured":"Callender, A. A., Franco-Watkins, A. M., & Roberts, A. S. (2016). Improving metacognition in the classroom through instruction, training, and feedback. Metacognition and Learning, 11, 215\u2013235.","journal-title":"Metacognition and Learning"},{"key":"416_CR4","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/s11858-006-0012-1","volume":"39","author":"U D\u2019Ambrosio","year":"2007","unstructured":"D\u2019Ambrosio, U. (2007). The role of mathematics in educational systems. ZDM Mathematics Education, 39, 173\u2013181.","journal-title":"ZDM Mathematics Education"},{"key":"416_CR5","doi-asserted-by":"crossref","unstructured":"Demszky, D., & Hill, H. (2023). The NCTE Transcripts: A Dataset of Elementary Math Classroom Transcripts. In Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023) (pp. 528-538).","DOI":"10.18653\/v1\/2023.bea-1.44"},{"key":"416_CR6","unstructured":"Dettmers, T., Pagnoni, A., Holtzman, A., & Zettlemoyer, L. (2024). Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems, 36."},{"key":"416_CR7","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Long and Short Papers) (Vol. 1, pp. 4171\u20134186)."},{"key":"416_CR8","unstructured":"DuBay, W. H. (2004). The principles of readability. Online Submission."},{"key":"416_CR9","doi-asserted-by":"crossref","unstructured":"Ernest, P., Skovsmose, O., Van Bendegem, J. P., Bicudo, M., Miarka, R., Kvasz, L., & Moeller, R. (2016). The philosophy of mathematics education. Springer Nature.","DOI":"10.1007\/978-3-319-40569-8"},{"issue":"5","key":"416_CR10","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1037\/h0062427","volume":"35","author":"JN Farr","year":"1951","unstructured":"Farr, J. N., Jenkins, J. J., & Paterson, D. G. (1951). Simplification of flesch reading ease formula. Journal of Applied Psychology, 35(5), 333.","journal-title":"Journal of Applied Psychology"},{"key":"416_CR11","unstructured":"Feng, Y., Jiang, J., Tang, M., Jin, R., & Gao, Y. (2021). Rethinking Supervised Pre-Training for Better Downstream Transferring. In International Conference on Learning Representations."},{"issue":"3","key":"416_CR12","doi-asserted-by":"publisher","first-page":"113","DOI":"10.25164\/SEP.2017040202","volume":"4","author":"Y Gao","year":"2017","unstructured":"Gao, Y., Zhang, P. P., Wen, S. F., & Chen, Y. G. (2017). Challenge, opportunity and development: Influencing factors and tendencies of curriculum innovation on undergraduate nursing education in the mainland of china. Chinese Nursing Research, 4(3), 113\u2013116.","journal-title":"Chinese Nursing Research"},{"issue":"1","key":"416_CR13","first-page":"34","volume":"6","author":"K Guill","year":"2014","unstructured":"Guill, K., & Bos, W. (2014). Effectiveness of private tutoring in mathematics with regard to subjective and objective indicators of academic achievement. Journal for Educational Research Online, 6(1), 34\u201367.","journal-title":"Journal for Educational Research Online"},{"key":"416_CR14","doi-asserted-by":"crossref","unstructured":"Gururangan, S., Marasovi\u0107, A., Swayamdipta, S., Lo, K., Beltagy, I., Downey, D., & Smith, N. A. (2020). Don\u2019t Stop Pretraining: Adapt Language Models to Domains and Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 8342-8360).","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"416_CR15","doi-asserted-by":"crossref","unstructured":"Howard, J., & Ruder, S. (2018). Universal language model fine-tuning for text classification. In ACL 2018-56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 1, pp. 328-339). Association for Computational Linguistics.","DOI":"10.18653\/v1\/P18-1031"},{"key":"416_CR16","unstructured":"Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., et al. (2021). Lora: Low- rank adaptation of large language models. arXiv preprint arXiv:2106.09685."},{"key":"416_CR17","doi-asserted-by":"crossref","unstructured":"Hussain, S., Muhsin, Z., Salal, Y., Theodorou, P., Kurto\u011flu, F., & Hazarika, G. (2019). Prediction model on student performance based on internal assessment using deep learning. International Journal of Emerging Technologies in Learning, 14(8).","DOI":"10.3991\/ijet.v14i08.10001"},{"issue":"2","key":"416_CR18","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1086\/648186","volume":"58","author":"S Kim","year":"2010","unstructured":"Kim, S., & Lee, J.-H. (2010). Private tutoring and demand for education in south korea. Economic Development and Cultural Change, 58(2), 259\u2013296.","journal-title":"Economic Development and Cultural Change"},{"key":"416_CR19","doi-asserted-by":"crossref","unstructured":"Ladhak, F., Durmus, E., Suzgun, M., Zhang, T., Jurafsky, D., McKeown, K., & Hashimoto, T. B. (2023). When do pre-training biases propagate to downstream tasks? a case study in text summarization. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics (pp. 3206-3219).","DOI":"10.18653\/v1\/2023.eacl-main.234"},{"key":"416_CR20","doi-asserted-by":"crossref","unstructured":"Leinonen, J., Hellas, A., Sarsa, S., Reeves, B., Denny, P., Prather, J., & Becker, B. A. (2023). Using large language models to enhance programming error messages. Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1, 563\u2013569.","DOI":"10.1145\/3545945.3569770"},{"key":"416_CR21","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1007\/s40593-020-00235-x","volume":"31","author":"C Li","year":"2021","unstructured":"Li, C., & Xing, W. (2021). Natural language generation using deep learning to support MOOC learners. International Journal of Artificial Intelligence in Education, 31, 186\u2013214.","journal-title":"International Journal of Artificial Intelligence in Education"},{"issue":"3","key":"416_CR22","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1080\/10494820.2022.2115076","volume":"32","author":"C Li","year":"2024","unstructured":"Li, C., Xing, W., & Leite, W. (2024). Using fair AI to predict students\u2019 math learning outcomes in an online platform. Interactive Learning Environments, 32(3), 1117\u20131136.","journal-title":"Interactive Learning Environments"},{"key":"416_CR23","unstructured":"Liu, H., Xie, S. M., Li, Z., & Ma, T. (2023a). Same pre-training loss, better down- stream: Implicit bias matters for language models. International Conference on Machine Learning, 22188\u201322214."},{"key":"416_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., He, X., Liu, L., Liu, T., & Zhai, X. (2023b). Context matters: A strategy to pre-train language model for science education. International Conference on Artificial Intelligence in Education, 666\u2013674.","DOI":"10.1007\/978-3-031-36336-8_103"},{"key":"416_CR25","unstructured":"Liu, Z., Qiao, A., Neiswanger, W., Wang, H., Tan, B., Tao, T., Li, J., Wang, Y., Sun, S., Pangarkar, O., et al. (2023c). Llm360: Towards fully transparent open-source llms. arXiv preprint arXiv:2312.06550."},{"key":"416_CR26","unstructured":"MacAvaney, S., Macdonald, C., Murray-Smith, R., & Ounis, I. (2021). IntenT5: Search Result Diversification using Causal Language Models. arXiv e-prints, arXiv-2108."},{"key":"416_CR27","unstructured":"Matelsky, J. K., et al. (2023). A large language model-assisted education tool to provide feedback on open-ended responses. arXiv preprint arXiv:2308.02439."},{"key":"416_CR28","doi-asserted-by":"crossref","unstructured":"McNamara, D. S., Allen, L. K., Crossley, S. A., Dascalu, M., & Perret, C. A. (2017). Natural Language Processing and Learning Analytics. Grantee Submission.","DOI":"10.18608\/hla17.008"},{"key":"416_CR29","doi-asserted-by":"crossref","unstructured":"Moore, S., Tong, R., Singh, A., Liu, Z., Hu, X., Lu, Y., Liang, J., Cao, C., Khosravi, H., Denny, P., et al. (2023). Empowering education with llms-the next- gen interface and content generation. International Conference on Artificial Intelligence in Education, 32\u201337.","DOI":"10.1007\/978-3-031-36336-8_4"},{"issue":"11","key":"416_CR30","doi-asserted-by":"publisher","first-page":"217","DOI":"10.3390\/computers12110217","volume":"12","author":"R Nakamoto","year":"2023","unstructured":"Nakamoto, R., Flanagan, B., Yamauchi, T., Dai, Y., Takami, K., & Ogata, H. (2023). Enhancing automated scoring of math self-explanation quality using llm-generated datasets: A semi-supervised approach. Computers, 12(11), 217.","journal-title":"Computers"},{"key":"416_CR31","unstructured":"Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., et al. (2023). A comprehensive overview of large language models. arXiv preprint arXiv:2307.06435."},{"key":"416_CR32","doi-asserted-by":"crossref","unstructured":"Niklaus, J., & Giofr\u00b4e, D. (2022). Budgetlongformer: Can we cheaply pretrain a sota legal language model from scratch? arXiv preprint arXiv:2211.17135.","DOI":"10.18653\/v1\/2023.sustainlp-1.11"},{"key":"416_CR33","doi-asserted-by":"crossref","unstructured":"Ogueji, K., Zhu, Y., & Lin, J. (2021). Small data? no problem! exploring the viability of pretrained multilingual language models for low-resourced languages. In Proceedings of the 1st Workshop on Multilingual Representation Learning (pp. 116-126).","DOI":"10.18653\/v1\/2021.mrl-1.11"},{"key":"416_CR34","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., ... & Chintala, S. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32."},{"issue":"8","key":"416_CR35","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI Blog, 1(8), 9.","journal-title":"OpenAI Blog"},{"issue":"1","key":"416_CR36","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., et al. (2020). Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 21(1), 5485\u20135551.","journal-title":"The Journal of Machine Learning Research"},{"issue":"4","key":"416_CR37","doi-asserted-by":"publisher","first-page":"809","DOI":"10.3390\/electronics12040809","volume":"12","author":"F Safarov","year":"2023","unstructured":"Safarov, F., Kutlimuratov, A., Abdusalomov, A. B., Nasimov, R., & Cho, Y. I. (2023). Deep learning recommendations of e-education based on clustering and sequence. Electronics, 12(4), 809.","journal-title":"Electronics"},{"issue":"1","key":"416_CR38","doi-asserted-by":"publisher","first-page":"e103","DOI":"10.52225\/narra.v3i1.103","volume":"3","author":"M Sallam","year":"2023","unstructured":"Sallam, M., et al. (2023). Chatgpt applications in medical, dental, pharmacy, and public health education: A descriptive study highlighting the advantages and limitations. Narra J, 3(1), e103\u2013e103.","journal-title":"Narra J"},{"key":"416_CR39","doi-asserted-by":"crossref","unstructured":"Sellam, T., Das, D., & Parikh, A. P. (2020). Bleurt: Learning robust metrics for text generation. arXiv preprint arXiv:2004.04696.","DOI":"10.18653\/v1\/2020.acl-main.704"},{"key":"416_CR40","unstructured":"Shen, J. T., Yamashita, M., Prihar, E., Heffernan, N., Wu, X., Graff, B., & Lee, D. (2021). Mathbert: A pre-trained language model for general nlp tasks in mathematics education. arXiv preprint arXiv:2106.07340."},{"key":"416_CR41","doi-asserted-by":"crossref","unstructured":"Song, Y., Li, C., Xing, W., Li, S., & Lee, H. H. (2024, March). A Fair Clustering Approach to Self-Regulated Learning Behaviors in a Virtual Learning Environment. In Proceedings of the 14th Learning Analytics and Knowledge Conference (pp. 771-778).","DOI":"10.1145\/3636555.3636863"},{"key":"416_CR42","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M. A., Lacroix, T., ... & Lample, G. (2023a). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971."},{"key":"416_CR43","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., et al. (2023b). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288."},{"key":"416_CR44","unstructured":"Veyseh, A. P. B., Meister, N., Yoon, S., Jain, R., Dernoncourt, F., & Nguyen, T. H. (2022). Macronym: A large-scale dataset for multilingual and multi-domain acronym extraction. arXiv preprint arXiv:2202.09694."},{"key":"416_CR45","doi-asserted-by":"crossref","unstructured":"Wang, S., Khabsa, M., & Ma, H. (2020). To Pretrain or Not to Pretrain: Examining the Benefits of Pretrainng on Resource Rich Tasks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (pp. 2209-2213).","DOI":"10.18653\/v1\/2020.acl-main.200"},{"key":"416_CR46","unstructured":"Wang, B., & Komatsuzaki, A. (2022). GPT-J-6B: a 6 billion parameter autoregressive language model (2021). URL https:\/\/github.com\/kingoflolz\/mesh-transformer-jax."},{"key":"416_CR47","unstructured":"Wang, P., Li, L., Shao, Z., Xu, R. X., Dai, D., Li, Y., ... & Sui, Z. (2023). Math-shepherd: Verify and reinforce llms step-by-step without human annotations. CoRR, abs\/2312.08935."},{"key":"416_CR48","doi-asserted-by":"crossref","unstructured":"Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., ... & Rush, A. M. (2020). Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations (pp. 38-45).","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"416_CR49","doi-asserted-by":"crossref","unstructured":"Xiao, C., Xu, S. X., Zhang, K., Wang, Y., & Xia, L. (2023). Evaluating reading com- prehension exercises generated by llms: A showcase of chatgpt in education applications. Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023), 610\u2013625.","DOI":"10.18653\/v1\/2023.bea-1.52"},{"issue":"3","key":"416_CR50","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1177\/0735633118757015","volume":"57","author":"W Xing","year":"2019","unstructured":"Xing, W., & Du, D. (2019). Dropout prediction in MOOCs: Using deep learning for personalized intervention. Journal of Educational Computing Research, 57(3), 547\u2013570.","journal-title":"Journal of Educational Computing Research"},{"key":"416_CR51","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.chb.2014.09.034","volume":"47","author":"W Xing","year":"2015","unstructured":"Xing, W., Guo, R., Petakovic, E., & Goggins, S. (2015). Participation-based student final performance prediction model through interpretable Genetic Programming: Integrating learning analytics, educational data mining and theory. Computers in human behavior, 47, 168\u2013181.","journal-title":"Computers in human behavior"},{"key":"416_CR52","unstructured":"Yu, L., Jiang, W., Shi, H., Yu, J., Liu, Z., Zhang, Y., ... & Liu, W. (2023). Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284."},{"key":"416_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, F., Xing, W., & Li, C. (2023, March). Predicting Students\u2019 Algebra I Performance using Reinforcement Learning with Multi-Group Fairness. In LAK23: 13th International Learning Analytics and Knowledge Conference (pp. 657-662).","DOI":"10.1145\/3576050.3576104"},{"issue":"8","key":"416_CR54","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1109\/TKDE.2013.39","volume":"26","author":"ML Zhang","year":"2013","unstructured":"Zhang, M. L., & Zhou, Z. H. (2013). A review on multi-label learning algorithms. IEEE Transactions on Knowledge and Data Engineering, 26(8), 1819\u20131837.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"416_CR55","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019). Bertscore: Evaluating text generation with bert.arXiv preprint arXiv:1904.09675."},{"key":"416_CR56","unstructured":"Zhang, Y., & Wallace, B. (2015). A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification. arXiv preprint arXiv:1510.03820."}],"container-title":["International Journal of Artificial Intelligence in Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40593-024-00416-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40593-024-00416-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40593-024-00416-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T18:12:51Z","timestamp":1772647971000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40593-024-00416-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,9]]},"references-count":56,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["416"],"URL":"https:\/\/doi.org\/10.1007\/s40593-024-00416-y","relation":{},"ISSN":["1560-4292","1560-4306"],"issn-type":[{"value":"1560-4292","type":"print"},{"value":"1560-4306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,9]]},"assertion":[{"value":"20 June 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}