ChatGPT’s pedagogical approach and the potential for hidden curriculum through school context proxies
DOI:
https://doi.org/10.32674/nyqmx528Keywords:
Generative AI, mathematics education, educational equity, mathematics pedagogyAbstract
This study investigates ChatGPT-4's pedagogical approach through mathematics lesson plans and examines how school context descriptors influence its output. We generated 45 individual eighth-grade probability lesson plans across three conditions: a baseline prompt, a "Successful School" context, and a "Struggling School" context. Content analysis of the lesson plans and 368 teacher-action verbs revealed that the LLM favored a direct instruction model (across all conditions) and shifted in specific ways in response to school descriptors. "Successful School" prompts generated lessons with additional mathematics concepts and advanced technology integration, whereas "Struggling School" prompts produced lessons with more monitoring of students’ progress, reinforcement activities, and attention to socioemotional support. These findings suggest that LLMs may replicate patterns of educational stratification.
References
Adams, G. L., & Engelmann, S. (1996). Research on Direct Instruction: 25 years beyond DISTAR. Educational Achievement Systems. https://www.thalesacademy.org/assets/docs/DI-25_Yrs_Beyond.pdf
Aga, Z. G., Sawyer, A. G., & Wolfe, M. (2024). More confidence more critical: Investigating secondary mathematics preservice teachers’ use of an artificial intelligence chatbot as a curriculum development tool. American Journal of Creative Education, 7(2), 63–78. https://doi.org/10.55284/ajce.v7i2.1278
Anyon, J. (1980). Social class and the hidden curriculum of work. Journal of Education, 162(1), 67–92. https://doi.org/10.1177/002205748016200106
Bardol, F. (2025). ChatGPT reads your tone and responds accordingly—until it does not—emotional framing induces bias in LLM outputs (Unpublished manuscript). arXiv. https://doi.org/10.48550/arXiv.2507.21083
Bender, E. M., Gebru, T., McMillan-Major, A., & Shmitchell, S. (2021). On the dangers of stochastic parrots: Can language models be too big? Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (pp. 610–623). Association for Computing Machinery. https://doi.org/10.1145/3442188.3445922
Biton, Y., & Segal, R. (2025). Learning to craft and critically evaluate prompts: The role of generative AI (ChatGPT) in enhancing pre-service mathematics teachers' TPACK and problem-posing skills. International Journal of Education in Mathematics, Science, and Technology, 13(1), 202–223. https://doi.org/10.46328/ijemst.4654
Broutin, M. S. T. (2024). Exploring mathematics teacher candidates' instrumentation process of generative artificial intelligence for developing lesson plans. Yükseköğretim Dergisi, 14(1), 165–176. https://doi.org/10.53478/yuksekogretim.1347061
Buchholtz, N., & Huget, J. (2024). ChatGPT as a reflection tool to promote the lesson planning competencies of pre-service teachers. In E. Faggiano, A. Clark-Wilson, M. Tabach, & H.-G. Weigand (Eds.), Proceedings of the 17th ERME Topic Conference MEDA 4 (pp. 129–136). University of Bari Aldo Moro.
Cameron, S., & Mesiti, C. (2024). What kind of mathematics teacher is ChatGPT? Identifying the pedagogical practices referenced by generative AI tools when preparing lesson plans. In J. Višňovská, E. Ross, & S. Getenet (Eds.), Surfing the waves of mathematics education: Proceedings of the 46th annual conference of the Mathematics Education Research Group of Australasia (pp. 135–142). MERGA.
Celik, I., Dindar, M., Muukkonen, H., & Järvelä, S. (2022). The promises and challenges of artificial intelligence for teachers: A systematic review of research. TechTrends, 66(4), 616–630. https://doi.org/10.1007/s11528-022-00715-y
Cheng, J., Wang, C., & Chen, B. (2025). Evaluating student agency in AI-generated lesson plans. In A. Rajala, A. Cortez, R. Hofmann, A. Jornet, H. Lotz-Sisitka, & L. Markauskaite (Eds.), Proceedings of the 19th International Conference of the Learning Sciences (pp. 2953-2955). International Society of the Learning Sciences.
Chu, H. & Rubel, L. (2010). Learning to teach mathematics in urban high schools: Untangling the threads of interwoven narratives. Journal of Urban Mathematics Education, 3(2), 57–76. https://doi.org/10.21423/jume-v3i2a50
Dilling, F., & Herrmann, M. (2024). Using large language models to support pre-service teachers mathematical reasoning—an exploratory study on ChatGPT as an instrument for creating mathematical proofs in geometry. Frontiers in Artificial Intelligence, 7. https://doi.org/10.3389/frai.2024.1460337
Diversity in Mathematics Education Center for Learning and Teaching. (2007). Culture, race, power and mathematics education. In F. K. Lester (Ed.), Second handbook of research on mathematics teaching and learning (pp. 405–433). Information Age Publishing.
Engelmann, S., & Becker, W. C. (1978). Systems for basic instruction: Theory and applications. In A. C. Catania & T. A. Brigham (Eds.), Handbook of applied behavior analysis (pp. 325–377). Irvington.
Etgar, R., Guttmann, R., Taub-Tabib, H., & Shmueli, E. (2024). Implicit bias in LLMs: Bias in financial advice based on implied gender (SSRN Scholarly Paper No. 4930361). https://doi.org/10.2139/ssrn.4930361
Gómez Marchant, C. N., & Hardison, H. (2024). In the shadows of burgeoning colossi: The whiteness of AI in mathematics teacher education. AMTE Connections, 33(4), 1–6. https://amte.net/sites/amte.net/files/Connections(Gomez%20Marchant).pdf
Gurl, T., Markinson, M., & Artzt, A. F. (2024 online; 2025 in print). Using ChatGPT as a lesson planning assistant in secondary mathematics teacher education. Digital Experiences in Mathematics Education. https://doi.org/10.1007/s40751-024-00162-9
Haberman, M. (2010). The pedagogy of poverty versus good teaching. Phi Delta Kappan, 92(2), 81–87. https://doi.org/10.1177/003172171009200223 (Original work published 1991)
Hiebert, J., Carpenter, T. P., Fennema, E., Fuson, K., Wearne, D., Murray, H., Olivier, A., & Human, P. (1996). Problem solving as a basis for reform in curriculum and instruction: The case of mathematics. Educational Researcher, 25(4), 12–21. https://doi.org/10.3102/0013189X025004012
Hu, B., Zheng, L., Zhu, J., Ding, L., Wang, Y., & Gu, X. (2024). Teaching plan generation and evaluation With GPT-4: Unleashing the potential of LLM in instructional design. IEEE Transactions on Learning Technologies, 17, 1445–1459. https://www.doi.org/10.1109/TLT.2024.3384765
Karaman, M. R., & Göksu, İ. (2024). Are lesson plans created by ChatGPT more effective? An experimental study. International Journal of Technology in Education, 7(1), 107–127. https://doi.org/10.46328/ijte.607
Klein, D. (2003). A brief history of American K-12 mathematics education in the 20th century. http://www.csun.edu/~vcmth00m/AHistory.html
Kotek, H., Dockum, R., Sun, S., & Yalcin, S. (2023). Gender bias and stereotypes in large language models. Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency (pp. 1–22). https://doi.org/10.1145/3593013.3593988
Lampert, M. (1990). When the problem is not the question and the solution is not the answer: Mathematical knowing and teaching. American Educational Research Journal, 27(1), 29–63. https://doi.org/10.2307/1163068
Langer-Osuna, J. M. (2011). How Brianna became bossy and Kofi came out smart: Understanding the trajectories of identity and engagement for two group leaders in a mathematics classroom. Canadian Journal of Science, Mathematics and Technology Education, 11(3), 207–225. https://doi.org/10.1080/14926156.2011.595881
Leonardo Z., & Hunter M. (2007). Imagining the urban: The politics of race, class, and schooling. In Pink W., Noblit G. (Eds.), International handbook of urban education (pp. 779–802). Springer.
Li, Y., Liu, J., & Yang, S. (2024). Is ChatGPT a good middle school teacher? An exploration of its role in instructional design. In Proceedings of the 3rd International Conference on New Media Development and Modernized Education. https://doi.org/10.4108/eai.13-10-2023.2341343
Lo, C. (2023). What is the impact of ChatGPT on education? A rapid review of the literature. Education Sciences, 13(4), 410. https://doi.org/10.3390/educsci13040410
Louie, N. & Rubel, L. (n.d.).
Lubienski, S. T. (2000). Problem solving as a means toward mathematics for all: An exploratory look through a class lens. Journal for Research in Mathematics Education, 31(4), 454-482. https://doi.org/10.2307/749653
Michaels, S., O’Connor, C., & Resnick, L. B. (2008). Deliberative discourse idealized and realized: Accountable talk in the classroom and in civic life. Studies in Philosophy and Education, 27, 283–297. https://doi.org/10.1007/s11217-007-9071-1
Munter, C., Stein, M. K., & Smith, M. S. (2015). Dialogic and direct instruction: Two distinct models of mathematics instruction and the debate(s) surrounding them. Teachers College Record, 117(11), 1–32. https://doi.org/10.1177/016146811511701102
Noble, S. U. (2018). Algorithms of oppression: How search engines reinforce racism. New York University Press.
Naresh, N., Yilmaz, Y., & Galanti, T. (2024). Leveraging the potential of AI as a partner in teaching. AMTE Connections https://amte.net/connections/2024/05/connections-thematic-articles-artificial-intelligence-mathematics-teacher
National Center for Education Statistics. (2023). Concentration of public school students eligible for free or reduced-price lunch. U.S. Department of Education, Institute of Education Sciences. https://nces.ed.gov/programs/coe/indicator/clb
National Council of Teachers of Mathematics (1989). Curriculum and evaluation standards for school mathematics. National Council of Teachers of Mathematics.
National Council of Teachers of Mathematics (2000). Principles and standards for school mathematics. National Council of Teachers of Mathematics.
Nguyen, T. N., & Truong, H. T. (2025). Trends and emerging themes in the effects of generative artificial intelligence in education: A systematic review. Eurasia Journal of Mathematics, Science and Technology Education, 21(4), em2613. https://doi.org/10.29333/ejmste/16124
Noble, S. U. (2018). Algorithms of oppression: How search engines reinforce racism. New York University Press.
Oakes, J. (2005). Keeping track: How schools structure inequality (2nd ed.). Yale University Press.
O'Connor, C., Michaels, S., Chapin, S., Harbaugh, A.G. (2017). The silent and the vocal: Participation and learning in whole-class discussion. Learning and Instruction, 48, 5-13. https://doi.org/10.1016/j.learninstruc.2016.11.003
Pepin, B., Buchholtz, N. & Salinas-Hernández, U. (2025). A scoping survey of ChatGPT in mathematics education. Digital Experiences in Mathematics Education, 11, 9–41. https://doi.org/10.1007/s40751-025-00172-1
Reinholz, D., Johnson, E., Andrews-Larson, C., Stone-Johnstone, A., Smith, J., Mullins, B., Fortune, N., Keene, K., & Shah, N. (2022). When active learning is inequitable: Women’s participation predicts gender inequities in mathematical performance. Journal for Research in Mathematics Education, 53(3), 204–226. https://doi.org/10.5951/jresematheduc-2020-0143
Remillard, J. T. & Kim, O. K.,(2020). Elementary mathematics curriculum materials: Designs for student learning and teacher enactment. Springer. https://doi.org/10.1007/978-3-030-38588-0_4
Resnick, L. B., Asterhan, C. S. C., Clarke, S. N., & with Schantz, F. (2018). Next generation research in dialogic learning. In G. E. Hall, Quinn, L. F., & Gollnick, D. M. (Eds.), Wiley Handbook on Teaching and Learning (pp. 323–338). Wiley-Blackwell. https://www.wiley.com/en-us/The+Wiley+Handbook+of+Teaching+and+Learning-p-9781118955871
Rosenshine, B. (2012). Principles of instruction: Research-based strategies that all teachers should know. American Educator, 36(1), 12–19. http://www.aft.org/newspubs/periodicals/ae
Rothstein, R. (2015). The racial achievement gap, segregated schools, and segregated neighborhoods: A constitutional insult. Race and Social Problems, 7(1), 21–30. https://doi.org/10.1007/s12552-014-9134-1
Rubel, L. (2017). Equity-directed instructional practices for secondary mathematics in urban schools. Journal of Urban Mathematics Education, 10(2), 66–105. https://jume-ojs-tamu.tdl.org/jume/index.php/JUME/article/view/324
Rubel, L. & Chu, H. (2012). Reinscribing urban: teaching high school mathematics in low income, urban communities of color. Journal of Mathematics Teacher Education, 15, 39–52. https://doi.org/10.1007/s10857-011-9200-1
Sapkota, B. & Bondurant, L. (2024). Assessing concepts, procedures, and cognitive demand of ChatGPT-generated mathematical tasks. International Journal of Technology in Education (IJTE), 7(2), 218-238. https://doi.org/10.46328/ijte.677
Schoenfeld, A. H. (2004). The math wars. Educational Policy, 18(1), 253–286. https://doi.org/10.1177/0895904803260042
Şimşek, N. (2025). Integration of ChatGPT in mathematical story-focused 5E lesson planning: Teachers and pre-service teachers' interactions with ChatGPT. Education and Information Technologies, 30, 11391–11462. https://doi.org/10.1007/s10639-024-13258-x
Stedy, Y., & Alfanta , D. (2024). The influence of the Direct Instruction learning model on student learning outcomes in elementary schools. Journal of Education Innovation and Curriculum Development, 2(3), 99–111. https://journals.iarn.or.id/index.php/educur/article/view/446
Stein, M. K., Engle, R. A., Smith, M. S., & Hughes, E. K. (2008). Orchestrating productive mathematical discussions: Five practices for helping teachers move beyond show and tell. Mathematical Thinking and Learning, 10(4), 313–340. https://doi.org/10.1080/10986060802229675
Stockard, J., Wood, T. W., Coughlin, C., & Rasplica Khoury, C. (2018). The effectiveness of direct instruction curricula: A meta-analysis of a half century of research. Review of Educational Research, 88(4), 479–507. https://doi.org/10.3102/0034654317751919
Trust, T., Maloy, R., Xu, C., & Pelletier, K. (2025). Civic education in the age of AI: Should we trust AI-generated lesson plans? Contemporary Issues in Technology and Teacher Education, 25(3). https://citejournal.org/volume-25/issue-3-25/social-studies/civic-education-in-the-age-of-ai-should-we-trust-ai-generated-lesson-plans
Walkington, C., Beauchamp, T., Lan, A., Pruitt-Britton, T. (2025). The efficiency of teacher-driven context Personalization in Mathematics with Large Language Models. In A.I. Cristea, E. Walker, Y. Lu, O.C. Santos, S. Isotani (Eds.) Artificial Intelligence in Education. Lecture Notes in Computer Science, vol 15880. Springer, Cham. https://doi.org/10.1007/978-3-031-98459-4_7
Walkington, C. (2025). The implications of generative artificial intelligence for mathematics education. School Science and Mathematics, 1–10. https://doi.org/10.1111/ssm.18356
Wardat, Y., Tashtoush, M., AlAli, R., & Jarrah, A. (2023). ChatGPT: A revolutionary tool for teaching and learning mathematics. Eurasia Journal of Mathematics, Science and Technology Education, 19(7), 2286. https://doi.org/10.29333/ejmste/13272
Wu, H. (1999). Basic skills versus conceptual understanding: A bogus dichotomy in mathematics education. American Educator, 23(3), 14–19, 50–52.
Yanar, B., & Ergene, Ö. (2025). Preservice teachers’ views on using ChatGPT for mathematics lesson planning: Opportunities and threats. Hacettepe Journal of Education, 40(1), 199–219. https://doi.org/10.16896/HUJE.2024127226
Yu, H. M., Lee, H., & Kim, S. H. (2025). Integrating ChatGPT in teacher education: Examining early childhood and elementary pre-service teachers’ experiences in AI-assisted math lesson planning. Journal of Research in Childhood Education, 1–23. https://doi.org/10.1080/02568543.2025.2579668
Additional Files
Published
Issue
Section
License
Copyright (c) 2026 Laurie Rubel, Shimrit Goidel
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) [year] [author]
This work is licensed under a Creative Commons Attribution 4.0 International License.
This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. https://creativecommons.org/licenses/by/4.0
Call for Special Issue Proposals 
