Use of AI for Generating and Grading Exam Questions in an Undergraduate English Linguistics Course

Tina Xu Geng; Raquel Raya-Porcel

doi:10.5294/edu.2026.29.1.6

Autores/as

Tina Xu Geng Autor/a Guangzhou College of Commerce https://orcid.org/0009-0004-2117-9617
Raquel Raya-Porcel Autor/a New College Durham https://orcid.org/0009-0009-4158-3883

DOI:

https://doi.org/10.5294/edu.2026.29.1.6

Palabras clave:

Calificación de exámenes generados por IA, ChatGPT, DeepSeek, evaluación de la educación, examen, inteligencia artificial

Resumen

Este estudio explora la aplicación de la inteligencia artificial (IA) en la generación y evaluación de preguntas de examen para cursos de lingüística inglesa a nivel universitario. En particular, se compara el desempeño de dos modelos de IA: ChatGPT y DeepSeek, en la creación de preguntas justas, coherentes y variadas, así como su eficacia en la calificación de respuestas de tipo subjetivo. Mediante un enfoque metodológico mixto que incluye análisis cuantitativo de contenidos generados por IA y evaluación comparativa con criterios humanos, el estudio identifica ventajas clave en eficiencia, objetividad y adaptabilidad, junto con desafíos tales como la comprensión contextual limitada y dificultades para evaluar respuestas creativas. Los hallazgos indican que, si bien la IA puede apoyar significativamente la docencia, su aplicación exitosa requiere ajustes minuciosos, supervisión continua y consideraciones éticas. El estudio concluye con recomendaciones prácticas dirigidas a educadores para optimizar el uso de herramientas de evaluación basadas en IA, con el fin de mantener estándares académicos y mejorar el rendimiento estudiantil.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Alers, H., Malinowska, A., Meghoe, G. y Apfel, E. (2024). Using ChatGPT-4 to grade open question exams. En Lecture Notes in Networks and Systems (vol. 919, pp. 1-9). Springer.

Bewersdorff, A., Seßler, K., Baur, A., Kasneci, E. y Nerdel, C. (2023). Assessing student errors in experimentation using artificial intelligence and large language models: A comparative study with human raters. Computers and Education: Artificial Intelligence, 5. https://doi.org/10.1016/j.caeai.2023.100177

Choi, J. H. (2024). How to use large language models for empirical legal research. Journal of Institutional and Theoretical Economics, 180(2), 214-233. https://doi.org/10.1628/jite-2024-0006

Chu, C.-H. y Liu, Y.-L. (2023). Augmented reality user interface design and experimental evaluation for human-robot collaborative assembly. Journal of Manufacturing Systems, 68, 313-324. https://doi.org/10.1016/j.jmsy.2023.04.007

Chu, H. y Liu, Y. (2024). Research on reforming the training model of master’s talents in design in ethnic regions of universities based on artificial intelligence. En 2024 The 9th International Conference on Information and Education Innovations (pp. 57-62). ACM. https://doi.org/10.1145/3664934.3664949

Cooper, G. (2023). Examining Science education in ChatGPT: An exploratory study of generative artificial intelligence. Journal of Science Education and Technology, 32(3), 444-452. https://doi.org/10.1007/s10956-023-10039-y

Daun, M. y Brings, J. (2023). How ChatGPT will change software engineering education. En ITiCSE 2023: Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education (vol. 1, pp. 110-116). ACM. https://doi.org/10.1145/3587102.3588815

Dai, W., Lin, J., Jin, H., Li, T., Tsai, Y.‑S., Gašević, D., y Chen, G. (2023). Can large language models provide feedback to students? A case study on ChatGPT. 2023 IEEE International Conference on Advanced Learning Technologies (ICALT), 323-325. https://doi.org/10.1109/ICALT58122.2023.00100

Deng, R., Jiang, M., Yu, X., Lu, Y. y Liu, S. (2025). Does ChatGPT enhance student learning? A systematic review and meta-analysis of experimental studies. Computers and Education, 227. https://doi.org/10.1016/j.compedu.2024.105224

Falchikov, N. y Goldfinch, J. (2000). Student peer assessment in higher education: A meta-analysis comparing peer and teacher marks. Review of Educational Research, 70(3), 287-322. https://doi.org/10.3102/00346543070003287

Farazouli, A., Cerratto-Pargman, T., Bolander-Laksov, K. y McGrath, C. (2024). Hello GPT! Goodbye home examination? An exploratory study of AI chatbots impact on university teachers’ assessment practices. Assessment and Evaluation in Higher Education, 49(3), 363-375. https://doi.org/10.1080/02602938.2023.2241676

Gencer, A. y Aydin, S. (2023). Can ChatGPT pass the thoracic surgery exam? American Journal of the Medical Sciences, 366(4), 291-295. https://doi.org/10.1016/j.amjms.2023.08.001

Kayaalp, M. E., Prill, R., Sezgin, E. A., Cong, T., Królikowska, A. y Hirschmann, M. T. (2025). DeepSeek versus ChatGPT: Multimodal artificial intelligence revolutionizing scientific discovery. From language editing to autonomous content generation—Redefining innovation in research and practice. Knee Surgery, Sports Traumatology, Arthroscopy, 33(5), 1553-1556. https://doi.org/10.1002/ksa.12628

Kung, J. E., Marshall, C., Gauthier, C., Gonzalez, T. A. y Jackson, J. B. (2023). Evaluating ChatGPT performance on the orthopaedic in-training examination. The Journal of Bone and Joint Surgery, 8(3), e23.00056. https://doi.org/10.2106/JBJS.23.0005

Leddo, J. (2021). Comparing the effectiveness of AI-powered educational software to human teachers. International Journal of Social Science and Economic Research, 6(3). https://doi.org/10.46609/IJSSER.2021.v06i03.015

Lee, G.-G. y Zhai, X. (2024). Using ChatGPT for science learning: A study on pre-service teachers’ lesson planning. IEEE Transactions on Learning Technologies, 17, 1683-1700. https://doi.org/10.1109/TLT.2024.3401457

Leiker, D., Finnigan, S., Gyllen, A. R. y Cukurova, M. (2023). Prototyping the use of Large Language Models (LLMs) for adult learning content creation at scale. arXiv:2306.01815, 3-7. https://doi.org/10.48550/arXiv.2306.01815

Mabrito, M. (2025). Collaborating with generative AI in the English classroom. International Journal of Technology, Knowledge and Society, 21(2), 1-23. https://doi.org/10.18848/1832-3669/CGP/v21i02/1-23

Markowitz, D. M. (2024). From complexity to clarity: How AI enhances perceptions of scientists and the public’s understanding of science. PNAS Nexus, 3(9). https://doi.org/10.1093/pnasnexus/pgae387

Markowitz, D. M., Hancock, J. T. y Bailenson, J. N. (2024). Linguistic markers of inherently false AI communication and intentionally false human communication: Evidence from hotel reviews. Journal of Language and Social Psychology, 43(1), 63-82. https://doi.org/10.1177/0261927X231200201

Mizumoto, A. y Eguchi, M. (2023). Exploring the potential of using an AI language model for automated essay scoring. Research Methods in Applied Linguistics, 2(2). https://doi.org/10.1016/j.rmal.2023.100050

Peng, Y., Malin, B. A., Rousseau, J. F., Wang, Y., Xu, Z., Xu, X., Weng, C. y Bian, J. (2025). From GPT to DeepSeek: Significant gaps remain in realizing AI in healthcare. Journal of Biomedical Informatics, 163, 104791. https://doi.org/10.1016/j.jbi.2025.104791

Pinto, G., Cardoso-Pereira, I., Monteiro, D., Lucena, D., Souza, A. y Gama, K. (2023). Large language models for education: Grading open-ended questions using ChatGPT. arXiv:2307.16696, 293-302. https://doi.org/10.1145/3613372.3614197

Rana, S., Sheshadri, T., Malhotra, N. y Mahabub Basha, S. (2024). Creating digital learning environments: Tools and technologies for success. En Transdisciplinary teaching and technological integration for improved learning: Case studies and practical approaches (pp. 1-21). IGI Global.

Sadler, P. M. y Good, E. (2006). The impact of self- and peer-grading on student learning. Educational Assessment, 11(1), 1-31. https://doi.org/10.1207/s15326977ea1101_1

Sun X., y Lin H. Investigación práctica sobre inteligencia artificial en la evaluación de exámenes - tomando como ejemplo las preguntas de geografía del examen de ingreso a la universidad de la provincia de Jiangsu de 2023. Geography Teaching, 2024(5): 21-23, 34.

Viera, A. J. y Garrett, J. M. (2008). Preliminary study of a school-based program to improve hypertension awareness in the community. Family Medicine, 40(4), 264-270.

Weber-Wulff, D., Anohina-Naumeca, A., Bjelobaba, S., Foltýnek, T., Guerrero-Dib, J., Popoola, O., Šigut, P. y Waddington, L. (2023). Testing of detection tools for AI-generated text. International Journal for Educational Integrity, 19(1). https://doi.org/10.1007/s40979-023-00146-z

Xu Wenbo, Zhou Xiaoping. “Exploración de la aplicación de modelos de lenguaje grandes tipo ChatGPT en la evaluación de cursos de enfermería - basado en pruebas con ChatGPT, Wenxin Yiyan y iFlytek Spark”. China Medical Education Technology, 2024, 38(5): 567-571.

Yeadon, W., Agra, E., Inyang, O.-O., Mackay, P. y Mizouri, A. (2024). Evaluating AI and human authorship quality in academic writing through physics essays. European Journal of Physics, 45(5). https://doi.org/10.1088/1361-6404/ad669d

Zhang, Y., Fen, B. W., Zhang, C. y Pi, S. (2024). Transforming music education through artificial intelligence: A Systematic literature review on enhancing music teaching and learning. International Journal of Interactive Mobile Technologies, 18(18), 76-93. https://doi.org/10.3991/ijim.v18i18.50545

Zupanc, K. y Bosnić, Z. (2020). Improvement of automated essay grading by grouping similar graders. Fundamenta Informaticae, 172(3), 239-259. https://doi.org/10.3233/FI-2020-1904