- Physical Review Journals
All JournalsPhysics Magazine

Physical Review Physics Education Research

Reuse & Permissions

It is not necessary to obtain permission to reuse this article or its components as it is available under the terms of the Creative Commons Attribution 4.0 International license. This license permits unrestricted use, distribution, and reproduction in any medium, provided attribution to the author(s) and the published article's title, journal citation, and DOI are maintained. Please note that some figures may have been included with permission from other third parties. It is your responsibility to obtain the proper permission from the rights holder directly for these figures.

Export citation

Export citation

Choose format for download:

Download Citation
  • Open Access

Effects of generative AI-mediated socratic dialogue on preservice physics teachers’ critical thinking in kinematics

Marcos Guerrero-Zambrano*, Bryan Valarezo-Chamba†, and Leonor Sanchez-Alvarado‡

Erick Lamilla-Rubio§

  • *Contact author: mguerreroz@unemi.edu.ec
  • †Contact author: bvalarezoc@unemi.edu.ec
  • ‡Contact author: lsancheza4@unemi.edu.ec
  • §Contact author: ealamill@espol.edu.ec, elamillar2@unemi.edu.ec
PDF

Phys. Rev. Phys. Educ. Res. 22, 020134 – Published 25 September, 2026

DOI: https://doi.org/10.1103/x7vq-17rq

Abstract

Initial physics teacher education frequently approaches kinematics problem solving as a procedural activity, with limited engagement in conceptual reasoning, argumentation, and metacognitive regulation. This study examines the effects of Socratic dialogue mediated by generative artificial intelligence (GAI), compared with teacher-guided Socratic dialogue alone, on discipline-specific critical thinking (CT) in one-dimensional kinematics. A concurrent mixed-methods, within-group preexperimental design was implemented with 18 preservice physics teachers working in small groups across two sequential phases using parallel kinematics problem sets. Because the instructional conditions were implemented in a fixed order, the observed differences cannot be disentangled from possible practice, learning, and carryover effects. In the first stage, students engaged in instructor-guided Socratic dialogue; in the second stage, the same structure was maintained while incorporating GAI-mediated Socratic support under instructor supervision. Critical thinking was assessed through an analytic rubric applied to written group solutions and complemented by Likert-scale surveys and open-ended responses. Rubric scores showed consistent improvement during the GAI-mediated phase across all groups, with no observed declines. Students also reported higher self-efficacy and intrinsic motivation, while cognitive load exhibited heterogeneous responses associated with the need for verification and epistemic control when interacting with GAI. These results suggest that integrating generative AI into a teacher-mediated Socratic framework can support critical thinking in kinematics, although the sequential preexperimental design requires cautious interpretation.

View figure in article

Physics Subject Headings (PhySH)

Article Text

References (48)

  1. J. L. Docktor, N. E. Strand, Jé P. Mestre, and B. H. Ross, Conceptual problem solving in high school physics, Phys. Rev. ST Phys. Educ. Res. 11, 020106 (2015).
  2. I. Sánchez Soto, M. A. Moreira, and C. Caballero Sahelices, Implementation of a proposal for meaningful learning of kinematics through problem solving, Ingeniare 17, 27 (2009).
  3. B. Mitrevski, Teaching critical thinking and problem solving in physics, AIP Conf. Proc. 2075, 180001 (2019).
  4. M. Ubaidillah, H. Hartono, P. Marwoto, W. Wiyanto, and B. Subali, How to improve critical thinking in physics learning? A systematic literature review, J. Educ. Cultural Psychol. Stud. 161 (2023).
  5. L. Møller Haase, J. Egelund Holgaard, and A. Kolmos, The complexity of engineering education in a mission driven PBL university, Transforming Engineering Education, OA ed. (Aalborg Universitetsforlag, 2023), pp. 172–177.
  6. Y.-R. Ho, B.-Y. Chen, and C.-M. Li, Thinking more wisely: Using the socratic method to develop critical thinking skills amongst healthcare students, BMC Med. Educ. 23, 173 (2023).
  7. S. Küchemann, S. Steinert, N. Revenga, M. Schweinberger, Y. Dinc, K. E. Avila, and J. Kuhn, Can ChatGPT support prospective teachers in physics task development?, Phys. Rev. Phys. Educ. Res. 19, 020128 (2023).
  8. N. H. Pulungan, M. Sirait, and E. M. Ginting, Analysis of linear motion kinematics on student’s critical thinking skillsbased on scientific inquiry, J. Phys.: Conf. Ser. 1811, 012006 (2021).
  9. J. D. Quiceno Osorio, La inteligencia artificial y el riesgo de una analogía invertida, Sophia Colección de Filosofía de la Educación 39, 315 (2025).
  10. A. Recio Sastre, La pregunta por la enseñanza de la ética como límite de la inteligencia artificial, Sophia, Colección de Filosofía de la Educación 39, 53 (2025).
  11. H. Barrios Tao, Configuración de subjetividades mediante sistemas de inteligencia artificial, Sophia, Colección de Filosofía de la Educación 39, 83 (2025).
  12. R. A. Reza Flores, R. M. Vicari, C. Galafassi, and M. Usart Rodríguez, Percepción del docente sobre la otredad en la era de la inteligencia artificial, Sophia, Colección de Filosofía de la Educación 39, 281 (2025).
  13. N. A. Zambrano-González and J. Vallverdú Segura, Retos del aprendizaje en la era de las heurísticas artificiales, Sophia, Colección de Filosofía de la Educación 39, 167 (2025).10.17163/soph.n39.2025.05
  14. J. W. Creswell and V. L. Plano Clark, Designing and Conducting Mixed Methods Research, 3rd ed. (SAGE Publications, Thousand Oaks, CA, USA, 2017).
  15. J. W. Creswell and J. D. Creswell, Research Design: Qualitative, Quantitative, and Mixed Methods Approaches, 5th ed. (SAGE Publications, Thousand Oaks, CA, USA, 2017).
  16. R. H. Ennis, Ideal critical thinkers are disposed to, Inquiry 26, 4 (2011).
  17. D. F. Halpern, Thought and Knowledge: An Introduction to Critical Thinking, 5th ed. (Psychology Press, Taylor & Francis Group, New York London, 2014).
  18. R. Paul and L. Elder, The Miniature Guide to Critical Thinking Concepts and Tools (Bloomsbury Publishing PLC, London, UK, 2019).
  19. P. A. Facione, Critical Thinking: What it Is and Why it Counts, (Insight Assessment, 2023), https://insightassessment.com/iaresource/critical-thinking-what-it-is-and-why-i t-counts/.
  20. A. Field, Discovering Statistics Using IBM SPSS Statistics, 5th ed. (SAGE Publications Ltd, London, UK, 2018), Vol. 1.
  21. D. C. Howell, Statistical Methods for Psychology (Cengage Learning, Belmont, CA, USA, 2009).
  22. F. J. Gravetter and L. B. Wallnau, Statistics for the behavioral sciences, 10th ed. (Cengage Learning, Boston, MA 02210 USA, 2017). Vol. 1.
  23. World Medical Association, World medical association declaration of Helsinki: ethical principles for medical research involving human subjects, Jama, J Am Med Assoc 310, 2191 (2013).
  24. E. A. Buchanan and M. Zimmer, Internet research ethics, The Stanford Encyclopedia of Philosophy Fall, 2025 Ed. (2012).
  25. N. Mohd Razali and Y. Bee Wah, Power comparisons of shapiro-wilk, Kolmogorov-smirnov, lilliefors and Anderson-darling tests (2, 21 (2011).
  26. B. W. Yap and C. H. Sim, Comparisons of various types of normality tests, J. Stat. Comput. Simul. 81, 2141 (2011).
  27. H. D. Kimmel, Three criteria for the use of one-tailed tests, Psychol. Bull. 54, 351 (1957).
  28. C. M. Lombardi and S. H. Hurlbert, Misprescription and misuse of one-tailed tests, Austral Ecol. 34, 447 (2009).
  29. G. D. Ruxton and M. Neuhäuser, When should we use one-tailed hypothesis testing?, Methods Ecol. Evol. 1, 114 (2010).
  30. L. Wilkinson and M. Friendly, The History of the Cluster Heat Map, Am. Stat. 63, 179 (2009).
  31. C. Ware, Information Visualization, 3rd ed. (Data Visualization Research Lab, University of New Hampshire, Durham, USA, 2012), Vol. 1.
  32. B. Rogowitz and L. Treinish, Data visualization: The end of the rainbow, IEEE Spectrum 35, 52 (1998).
  33. E. Kasneci et al., ChatGPT for good? On opportunities and challenges of large language models for education, Learn. Individ. Differ. 103, 102274 (2023).
  34. W. Holmes and I. Tuomi, State of the art and practice in AI in education, Eur. J. Educ. 57, 542 (2022).
  35. A. M. Al-Abdullatif and M. A. Alsubaie, ChatGPT in learning: Assessing students’ use intentions through the lens of perceived value and the influence of AI literacy, Behav. Sci. 14, 845 (2024).
  36. V. Braun and V. Clarke, Conceptual and design thinking for thematic analysis, Qualitative Psychol. 9, 3 (2022).
  37. A. Killett, P. E. Langdon, H. Ryan, C. Shiggins, R. Heywood, O. F. Jimoh, M. Redley, and K. Bunning, Inclusion of adults with conditions that have the potential to affect capacity and or communication in research: triangulation from a mixed-methods study of current practice and values across multiple stakeholders, BMJ Open 13, e068366 (2023).
  38. S. Tonkin-Crine, S. Anthierens, K. Hood, L. Yardley, J. W. L. Cals, N. A. Francis, S. Coenen, A. W. van der Velden, M. Godycki-Cwirko, C. Llor, C. C. Butler, T. J. M. Verheij, H. Goossens, and P. Little and on behalf of the GRACE IN TRO/CHAMP consortium, Discrepancies between qualitative and quantitative evaluation of randomised controlled trial results: Achieving clarity through mixed methods triangulation, Implementation Sci. 11, 66 (2016).
  39. G. Kestin, K. Miller, A. Klales, T. Milbourne, and G. Ponti, AI tutoring outperforms in-class active learning: An RCT introducing a novel research-based design in an authentic educational setting, Sci Rep 15, 17458 (2025).
  40. H. Fakour and M. Imani, Socratic wisdom in the age of AI: A comparative study of ChatGPT and human tutors in enhancing critical thinking skills, Front. Educ. 10, 1528603 (2025).
  41. J. Jabbour, K. Kleinbard, O. Miller, R. Haussman, and V. J. Reddi, SocratiQ: A generative AI-powered learning companion for personalized education and broader accessibility, in Proceedings of the Workshop on Computer Architecture Education (ACM, Tokyo Japan, 2025), pp. 1–10.
  42. Y. Ding, H. Hu, J. Zhou, Q. Chen, B. Jiang, and L. He, Boosting large language models with Socratic method for conversational mathematics teaching, in Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, CIKM ’24 (Association for Computing Machinery, New York, NY, USA, 2024), pp. 3730–3735.
  43. Y. P. Chavesta Incio and M. d. l. Sánchez Trujillo, El pensamiento crítico en los estudiantes de una Escuela Nacional Superior de Arte, Revista de Estudios y Experiencias en Educación 22, 65 (2023).
  44. B. Gregorcic, G. Polverini, and A. Sarlah, ChatGPT as a tool for honing teachers’ Socratic dialogue skills, Phys. Educ. 59, 045005 (2024).
  45. E. Tufino and B. Gregorcic, Creating a customisable Socratic AI physics tutor, Phys. Educ. 60, 065037 (2025).
  46. E. M. Torralba, Generative AI scaffolding in physics education: A phenomenological analysis of its role and implications in STEM learning, Schrödinger 6, 175 (2025).
  47. A. Sirnoorkar, D. Zollman, J. T. Laverty, A. J. Magana, N. S. Rebello, and L. A. Bryan, Student and AI responses to physics problems examined through the lenses of sensemaking and mechanistic reasoning, Comput. Educ. 7, 100318 (2024).
  48. N. A. F. Shukor and K. Osman, The Role of artificial intelligence in developing critical thinking among science students: A systematic literature review, Int. J. Acad. Res. Prog. Educ. Dev. 14, 164 (2025)..

Outline

Information

Phys. Rev. Phys. Educ. Res. 22, 020134– Published 25 September, 2026
  • Received 12 February 2026
  • Accepted 4 August 2026
Crossmark - Check for updates button
Creative Commons Logo

Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.

Published by the American Physical Society

Sign In to Your Journals Account

Filter

Filter

Article Lookup

Enter a citation