Impacto de ChatGPT en los métodos de evaluación de un grado de Ingeniería Informática

  1. Roberto Rodríguez-Echeverría 1
  2. Juan D. Gutiérrez 1
  3. José M. Conejero 1
  4. Álvaro E. Prieto 1
  1. 1 Universidad de Extremadura
    info

    Universidad de Extremadura

    Badajoz, España

    ROR https://ror.org/0174shg90

Journal:
Actas de las Jornadas sobre la Enseñanza Universitaria de la Informática (JENUI)

ISSN: 2531-0607

Year of publication: 2023

Issue: 8

Pages: 33-40

Type: Article

DIALNET GOOGLE SCHOLAR lock_openRUA editor

More publications in: Actas de las Jornadas sobre la Enseñanza Universitaria de la Informática (JENUI)

Abstract

Generative Artificial Intelligence has undergone significant evolution over the last few years, especially in 2022. The artificial intelligence causing the most buzz in the academic world is ChatGPT, which provides an user interface that significantly simplifies the productive use of a large language model. These language models can parse and generate text with great speed and quality. Such language competences might have a relevant impact on teaching-learning methodologies and assessment methods. In order to analyze the possible impact of ChatGPT on assessment methods, in this work, we have used it to solve the exams of 15 Software Engineering subjects of a Computer Engineering degree. The results show that ChatGPT has an evident impact on assessment methods, because it can provide a correct answer to many questions and problems of different typology in multiple subjects. A detailed study of the results organized by types of questions and problems is provided as main contribution. Finally, some recommendations are derived from those results to guide in the design of assessment methods.

Bibliographic References

  • Michael James Bommarito y Daniel Martin Katz. GPT Takes the Bar Exam, 2022. Disponible en SSRN: https://ssrn.com/abstract=4314839.
  • Tom B Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, y Tom Henighan. Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems, 33, 2020.
  • José Divasón, F. Javier Martínez de Pisón, Ana Romero, y Eduardo Sáenz de Cabezón. Modelos de inteligencia artificial para asesorar el proceso evaluador de trabajos informáticos complejos. En Actas de las XXVII Jornadas de Enseñanza Universitaria de Informática, Jenui 2021, pp. 43 – 50, Valencia, julio 2021.
  • Aidan Gilson, Conrad Safranek, Thomas Huang, Vimig Socrates, Ling Chi, R. Andrew Taylor, y David Chartash. How does ChatGPT perform on the medical licensing exams? The implications of large language models for medical education and knowledge assessment, 2022. Disponible en medRxiv: https://www.medrxiv.org/ content/10.1101/2022.12.23.22283901v1.
  • Nora Kassner y Hinrich Schütze. Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly. En Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 7811– 7818, 2020.
  • Lars Lidén. Artificial stupidity: The art of intentional mistakes. AI game programming wisdom, 2:41–48, 2003.
  • Muneer M Alshater. Exploring the role of artificial intelligence in enhancing academic performance: A case study of ChatGPT, 12 2022. Disponible en SSRN: https://ssrn.com/abstract= 4312358.
  • Kyle Mahowald, Anna A. Ivanova, Idan A. Blank, Nancy Kanwisher, Joshua B. Tenenbaum, y Evelina Fedorenko. Dissociating language and thought in large language models: A cognitive perspective. arXiv:2301.06627v1, 2023. Disponible en arXiv: https://arxiv.org/abs/2301.06627.
  • Warren S McCulloch y Walter Pitts. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115–133, 1943.
  • OpenAI. ChatGPT: Optimizing Language Models for Dialogue, noviembre 2022. Disponible en https://openai.com/blog/chatgpt/.
  • Teo Susnjak. ChatGPT: The End of Online Exam Integrity? arXiv:2212.09292, 2022. Disponible en arXiv: https://arxiv.org/abs/2212.09292.
  • Edmundo (ed.) Tovar Caro. Actas de las III Jornadas de Enseñanza Universitaria de Informática, Jenui 1997, junio 1997.
  • Alan M. Turing. I.—Computing Machinery and Intelligence. Mind, LIX(236):433–460, 10 1950.
  • Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, e Illia Polosukhin. Attention is All you Need. Advances in neural information processing systems, 30, 2017.
  • Sebastian Wollny, Jan Schneider, Daniele Di Mitri, Joshua Weidlich, Marc Rittberger, y Hendrik Drachsler. Are we there yet? - A systematic literature review on chatbots in education. Frontiers in Artificial Intelligence, 4, 2021.
  • BigScience Workshop. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model. arXiv:2211.05100, 2022. Disponible en arXiv: https://arxiv.org/abs/2211.05100.
  • Xiaoming Zhai. ChatGPT user experience: Implications for education, 2022. Disponible en SSRN: https://ssrn.com/abstract=4312418.
  • Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, y Luke Zettlemoyer. OPT: Open pre-trained transformer language models. arXiv:2205.01068, 2022. Disponible en arXiv: https://arxiv.org/abs/2205.01068.
Data source: Dialnet