{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:38:37Z","timestamp":1784302717174,"version":"3.55.0"},"reference-count":56,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T00:00:00Z","timestamp":1776816000000},"content-version":"vor","delay-in-days":325,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Artificial Intelligence in Education"],"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\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":16,"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":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenglu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Owen","family":"Henkel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1446-889X","authenticated-orcid":false,"given":"Wanli","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sami","family":"Baral","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Heffernan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hai","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1007\/s40593-024-00416-y_bib1","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s11409-013-9107-6","article-title":"Process mining techniques for analysing patterns and strategies in students\u2019 self-regulated learning","volume":"9","author":"Bannert","year":"2014","journal-title":"Metacognition and Learning"},{"issue":"6","key":"10.1007\/s40593-024-00416-y_bib2","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1080\/09500782.2020.1842443","article-title":"From \u201cacademic language\u201d to the \u201clanguage of ideas\u201d: A disciplinary perspective on using language in k-12 settings","volume":"35","author":"Bunch","year":"2021","journal-title":"Language and Education"},{"key":"10.1007\/s40593-024-00416-y_bib3","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1007\/s11409-015-9142-6","article-title":"Improving metacognition in the classroom through instruction, training, and feedback","volume":"11","author":"Callender","year":"2016","journal-title":"Metacognition and Learning"},{"key":"10.1007\/s40593-024-00416-y_bib4","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/s11858-006-0012-1","article-title":"The role of mathematics in educational systems","volume":"39","author":"D\u2019Ambrosio","year":"2007","journal-title":"ZDM Mathematics Education"},{"key":"10.1007\/s40593-024-00416-y_bib5","doi-asserted-by":"crossref","first-page":"528","DOI":"10.18653\/v1\/2023.bea-1.44","article-title":"The NCTE Transcripts: A Dataset of Elementary Math Classroom Transcripts","author":"Demszky","year":"2023","journal-title":"Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)"},{"key":"10.1007\/s40593-024-00416-y_bib6","article-title":"Qlora: Efficient finetuning of quantized llms","volume":"36","author":"Dettmers","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1007\/s40593-024-00416-y_bib7","first-page":"4171","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","volume":"1","author":"Devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Long and Short Papers)"},{"key":"10.1007\/s40593-024-00416-y_bib8","article-title":"The principles of readability","author":"DuBay","year":"2004","journal-title":"Online Submission."},{"key":"10.1007\/s40593-024-00416-y_bib9","series-title":"The philosophy of mathematics education.","author":"Ernest","year":"2016"},{"issue":"5","key":"10.1007\/s40593-024-00416-y_bib10","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1037\/h0062427","article-title":"Simplification of flesch reading ease formula","volume":"35","author":"Farr","year":"1951","journal-title":"Journal of Applied Psychology"},{"key":"10.1007\/s40593-024-00416-y_bib11","article-title":"Rethinking Supervised Pre-Training for Better Downstream Transferring","author":"Feng","year":"2021","journal-title":"International Conference on Learning Representations."},{"issue":"3","key":"10.1007\/s40593-024-00416-y_bib12","doi-asserted-by":"crossref","first-page":"113","DOI":"10.25164\/SEP.2017040202","article-title":"Challenge, opportunity and development: Influencing factors and tendencies of curriculum innovation on undergraduate nursing education in the mainland of china","volume":"4","author":"Gao","year":"2017","journal-title":"Chinese Nursing Research"},{"issue":"1","key":"10.1007\/s40593-024-00416-y_bib13","first-page":"34","article-title":"Effectiveness of private tutoring in mathematics with regard to subjective and objective indicators of academic achievement","volume":"6","author":"Guill","year":"2014","journal-title":"Journal for Educational Research Online"},{"key":"10.1007\/s40593-024-00416-y_bib14","doi-asserted-by":"crossref","first-page":"8342","DOI":"10.18653\/v1\/2020.acl-main.740","article-title":"Don\u2019t Stop Pretraining: Adapt Language Models to Domains and Tasks","author":"Gururangan","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"10.1007\/s40593-024-00416-y_bib15","series-title":"ACL 2018-56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)","first-page":"328","article-title":"Universal language model fine-tuning for text classification","author":"Howard","year":"2018"},{"key":"10.1007\/s40593-024-00416-y_bib16","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."},{"issue":"8","key":"10.1007\/s40593-024-00416-y_bib17","doi-asserted-by":"crossref","DOI":"10.3991\/ijet.v14i08.10001","article-title":"Prediction model on student performance based on internal assessment using deep learning","volume":"14","author":"Hussain","year":"2019","journal-title":"International Journal of Emerging Technologies in Learning"},{"issue":"2","key":"10.1007\/s40593-024-00416-y_bib18","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1086\/648186","article-title":"Private tutoring and demand for education in south korea","volume":"58","author":"Kim","year":"2010","journal-title":"Economic Development and Cultural Change"},{"key":"10.1007\/s40593-024-00416-y_bib19","first-page":"3206","article-title":"When do pre-training biases propagate to downstream tasks? a case study in text summarization","author":"Ladhak","year":"2023","journal-title":"Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics"},{"key":"10.1007\/s40593-024-00416-y_bib20","first-page":"563","article-title":"Using large language models to enhance programming error messages","author":"Leinonen","year":"2023","journal-title":"Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1"},{"key":"10.1007\/s40593-024-00416-y_bib21","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1007\/s40593-020-00235-x","article-title":"Natural language generation using deep learning to support MOOC learners","volume":"31","author":"Li","year":"2021","journal-title":"International Journal of Artificial Intelligence in Education"},{"issue":"3","key":"10.1007\/s40593-024-00416-y_bib22","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1080\/10494820.2022.2115076","article-title":"Using fair AI to predict students\u2019 math learning outcomes in an online platform","volume":"32","author":"Li","year":"2024","journal-title":"Interactive Learning Environments"},{"key":"10.1007\/s40593-024-00416-y_bib23","first-page":"22188","article-title":"Same pre-training loss, better down- stream: Implicit bias matters for language models","author":"Liu","year":"2023","journal-title":"International Conference on Machine Learning"},{"key":"10.1007\/s40593-024-00416-y_bib24","first-page":"666","article-title":"Context matters: A strategy to pre-train language model for science education","author":"Liu","year":"2023","journal-title":"International Conference on Artificial Intelligence in Education"},{"key":"10.1007\/s40593-024-00416-y_bib25","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":"10.1007\/s40593-024-00416-y_bib26","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":"10.1007\/s40593-024-00416-y_bib27","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":"10.1007\/s40593-024-00416-y_bib28","article-title":"Natural Language Processing and Learning Analytics","author":"McNamara","year":"2017","journal-title":"Grantee Submission."},{"key":"10.1007\/s40593-024-00416-y_bib29","first-page":"32","article-title":"Empowering education with llms-the next- gen interface and content generation","author":"Moore","year":"2023","journal-title":"International Conference on Artificial Intelligence in Education"},{"issue":"11","key":"10.1007\/s40593-024-00416-y_bib30","doi-asserted-by":"crossref","first-page":"217","DOI":"10.3390\/computers12110217","article-title":"Enhancing automated scoring of math self-explanation quality using llm-generated datasets: A semi-supervised approach","volume":"12","author":"Nakamoto","year":"2023","journal-title":"Computers"},{"key":"10.1007\/s40593-024-00416-y_bib31","unstructured":"Naveed, H., Khan, A. U., Qiu, S., Saqib, M., Anwar, S., Usman, M., Barnes, N., & Mian, A. (2023). A comprehensive overview of large language models. arXiv preprint arXiv:2307.06435."},{"key":"10.1007\/s40593-024-00416-y_bib32","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":"10.1007\/s40593-024-00416-y_bib33","doi-asserted-by":"crossref","first-page":"116","DOI":"10.18653\/v1\/2021.mrl-1.11","article-title":"Small data? no problem! exploring the viability of pretrained multilingual language models for low-resourced languages","author":"Ogueji","year":"2021","journal-title":"Proceedings of the 1st Workshop on Multilingual Representation Learning"},{"key":"10.1007\/s40593-024-00416-y_bib34","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"issue":"8","key":"10.1007\/s40593-024-00416-y_bib35","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"issue":"1","key":"10.1007\/s40593-024-00416-y_bib36","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"The Journal of Machine Learning Research"},{"issue":"4","key":"10.1007\/s40593-024-00416-y_bib37","doi-asserted-by":"crossref","first-page":"809","DOI":"10.3390\/electronics12040809","article-title":"Deep learning recommendations of e-education based on clustering and sequence","volume":"12","author":"Safarov","year":"2023","journal-title":"Electronics"},{"issue":"1","key":"10.1007\/s40593-024-00416-y_bib38","doi-asserted-by":"crossref","DOI":"10.52225\/narra.v3i1.103","article-title":"Chatgpt applications in medical, dental, pharmacy, and public health education: A descriptive study highlighting the advantages and limitations","volume":"3","author":"Sallam","year":"2023","journal-title":"Narra J"},{"key":"10.1007\/s40593-024-00416-y_bib39","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":"10.1007\/s40593-024-00416-y_bib40","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":"10.1007\/s40593-024-00416-y_bib41","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1145\/3636555.3636863","article-title":"A Fair Clustering Approach to Self-Regulated Learning Behaviors in a Virtual Learning Environment","author":"Song","year":"2024","journal-title":"Proceedings of the 14th Learning Analytics and Knowledge Conference"},{"key":"10.1007\/s40593-024-00416-y_bib42","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M. A., Lacroix, T., \u2026 & Lample, G. (2023a). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971."},{"key":"10.1007\/s40593-024-00416-y_bib43","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":"10.1007\/s40593-024-00416-y_bib44","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":"10.1007\/s40593-024-00416-y_bib45","doi-asserted-by":"crossref","first-page":"2209","DOI":"10.18653\/v1\/2020.acl-main.200","article-title":"To Pretrain or Not to Pretrain: Examining the Benefits of Pretrainng on Resource Rich Tasks","author":"Wang","year":"2020","journal-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics"},{"key":"10.1007\/s40593-024-00416-y_bib46","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":"10.1007\/s40593-024-00416-y_bib47","unstructured":"Wang, P., Li, L., Shao, Z., Xu, R. X., Dai, D., Li, Y., \u2026 & Sui, Z. (2023). Math-shepherd: Verify and reinforce llms step-by-step without human annotations. CoRR, abs\/2312.08935."},{"key":"10.1007\/s40593-024-00416-y_bib48","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","author":"Wolf","year":"2020","journal-title":"Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations"},{"key":"10.1007\/s40593-024-00416-y_bib49","doi-asserted-by":"crossref","first-page":"610","DOI":"10.18653\/v1\/2023.bea-1.52","article-title":"Evaluating reading com- prehension exercises generated by llms: A showcase of chatgpt in education applications","author":"Xiao","year":"2023","journal-title":"Proceedings of the 18th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2023)"},{"issue":"3","key":"10.1007\/s40593-024-00416-y_bib50","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1177\/0735633118757015","article-title":"Dropout prediction in MOOCs: Using deep learning for personalized intervention","volume":"57","author":"Xing","year":"2019","journal-title":"Journal of Educational Computing Research"},{"key":"10.1007\/s40593-024-00416-y_bib51","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1016\/j.chb.2014.09.034","article-title":"Participation-based student final performance prediction model through interpretable Genetic Programming: Integrating learning analytics, educational data mining and theory","volume":"47","author":"Xing","year":"2015","journal-title":"Computers in human behavior"},{"key":"10.1007\/s40593-024-00416-y_bib52","doi-asserted-by":"crossref","unstructured":"Yu, L., Jiang, W., Shi, H., Yu, J., Liu, Z., Zhang, Y., \u2026 & Liu, W. (2023). Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284.","DOI":"10.55846\/9789675492860"},{"key":"10.1007\/s40593-024-00416-y_bib53","first-page":"657","article-title":"Predicting Students\u2019 Algebra I Performance using Reinforcement Learning with Multi-Group Fairness","author":"Zhang","year":"2023","journal-title":"LAK23: 13th International Learning Analytics and Knowledge Conference"},{"issue":"8","key":"10.1007\/s40593-024-00416-y_bib54","doi-asserted-by":"crossref","first-page":"1819","DOI":"10.1109\/TKDE.2013.39","article-title":"A review on multi-label learning algorithms","volume":"26","author":"Zhang","year":"2013","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1007\/s40593-024-00416-y_bib55","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":"10.1007\/s40593-024-00416-y_bib56","unstructured":"Zhang, Y., & Wallace, B. (2015). A sensitivity analysis of (and practitioners\u2019 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:\/\/api.elsevier.com\/content\/article\/PII:S1560429226001228?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1560429226001228?httpAccept=text\/plain","content-type":"text\/plain","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":[[2026,5,18]],"date-time":"2026-05-18T06:21:43Z","timestamp":1779085303000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1560429226001228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":56,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["S1560429226001228"],"URL":"https:\/\/doi.org\/10.1007\/s40593-024-00416-y","relation":{},"ISSN":["1560-4292"],"issn-type":[{"value":"1560-4292","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Math-LLMs: AI Cyberinfrastructure with Pre-trained Transformers for Math Education","name":"articletitle","label":"Article Title"},{"value":"International Journal of Artificial Intelligence in Education","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1007\/s40593-024-00416-y","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"Copyright \u00a9 2024 International Artificial Intelligence in Education Society. Published by Elsevier Ltd","name":"copyright","label":"Copyright"}]}}