Evaluación de la inteligencia artificial generativa en el contexto de la automática: un análisis crítico

• Barragán, Antonio Javier ^[1] ; Aquino, Arturo ^[1] ; Enrique, Juan Manuel ^[1] ; Segura, Francisca ^[1] ; Martínez, Miguel Ángel ^[1] ; Andújar, José Manuel ^[1]
  1. [1] Universidad de Huelva

     Universidad de Huelva

     Huelva, España

     
• Localización: Jornadas de Automática, ISSN-e 3045-4093, Nº. 45, 2024
• Idioma: español
• DOI: 10.17979/ja-cea.2024.45.10733
• Títulos paralelos:
  • Evaluating generative artificial intelligence in the context of automatics: a critical analysis
• Enlaces
  • Texto completo
• Resumen
  • español

    La reciente proliferación de las inteligencias artificiales (IAs), en particular las IAs generativas, está impulsando una necesidad de transformación en la educación universitaria. La habilidad de las IAs para generar contenido, redactar informes, resúmenes y solucionar problemas de diversa complejidad, debería inducir una revisión de muchos de los métodos de evaluación tradicionales; o al menos, un reconocimiento de la capacidad del estudiantado para emplear estas herramientas en la ejecución de sus tareas. Este artículo tiene como objetivo evaluar las competencias de las principales IAs disponibles en la actualidad para llevar a cabo tareas asociadas con la ingeniería de control, tanto teóricas como prácticas. Los resultados indican que las IAs actuales todavía no pueden resolver problemas de control de manera efectiva, y tienden a recurrir a soluciones estándar que no siempre son apropiadas; no obstante, muestran un rendimiento satisfactorio respecto de conocimientos teóricos generales.

  • English

    The recent proliferation of artificial intelligences (AIs), particularly generative AIs, is driving a need for transformation inuniversity education. The ability of AIs to generate content, write reports, summaries and solve problems of varying complexity should prompt a review of many traditional assessment methods, or at least a recognition of students’ ability to employ these tools in the execution of their tasks. This paper aims to assess the competencies of the main AIs currently available for carrying out tasks associated with control engineering, both theoretical and practical. The results indicate that current AIs are not yet able to solve control problems effectively, and tend to resort to standard solutions that are not always appropriate; however, they show satisfactory performance with respect to general theoretical knowledge.

• Referencias bibliográficas
  • Bethencourt-Aguilar, A., Castellanos-Nieves, D., Sosa-Alonso, J. J., Area-Moreira, M., 2023. Use of generative adversarial networks (GANs)...
  • Divasón, J., de Pison, F. J. M., Romero, A., de Cabezón, E. S., 2023. Artificial intelligence models for assessing the evaluation process...
  • Google AI, 2024. Gemini.
  • Hemachandran, K., Verma, P., Pareek, P., Arora, N., Kumar, K. V. R., Ahanger, T., Pise, A., Ratna, R., 2022. Artificial intelligence: A universal...
  • Jiayu, Y., 2023. Challenges and opportunities of generative artificial intelligence in higher education student educational management. Advances...
  • Khalil, M., Er, E., 2023. Will chatgpt get you caught? Rethinking of plagiarism detection. In: Zaphiris, P., Ioannou, A. (Eds.), Learning...
  • Likert, R., 1932. A technique for the measurement of attitudes. Archives of Psychology, 1–55.
  • Lopez-Carreño, J., Calvo-Lavado, C., Azpilcueta-Vasquez, M., Zárate-Pérez, E., 2022. Artificial-intelligence-based school assistant for detecting...
  • Lund, B., Ting, W., 2023. Chatting about ChatGPT: How may AI and GPT impact academia and libraries? SSRN Electronic Journal. DOI: 10.2139/ssrn.4333415...
  • Meta Platforms, Inc., 2022. Llama 3. URL: https://llama.meta.com
  • Microsoft Corporation, 2024. Copilot Pro. URL: https://copilot.microsoft.com
  • OpenAI, 2022. ChatGPT 3.5. URL: https://chat.openai.com
  • Perplexity AI, 2022. Llama 3. URL: www.perplexity.ai
  • Popenici, S. A. D., Kerr, S., 2017. Exploring the impact of artificial intelligence on teaching and learning in higher education. Research...
  • Ruiz-Rojas, L. I., Acosta-Vargas, P., De-Moreta-Llovet, J., González- Rodríguez, M., 2023. Empowering education with generative artificial...
  • Rybiński, K., Kopciuszewska, E., 2020. Will artificial intelligence revolutionise the student evaluation of teaching? A big data study of...
  • Stone, C., 2023. Artificial intelligence in social work practice education. the potential use of generative ai for learning. The Journal of...
  • UNESCO, 2023. Guidance for generative AI in education and research. URL: https://www.unesco.org/en/articles/guidance-generative-ai-education-and-research
  • Walczak, K., Cellary, W., 2023. Challenges for higher education in the era of widespread access to generative AI. Economics and Business Review...
  • Wang, J., Tan, Z., Zhou, F., Hu, Z., Fu, B., Wang, Y., 2023. Evaluation of the influence of artificial intelligence on college students’ learning...
  • Wang, S., 2022. The day the AGI was born. URL: https://www.latent.space/p/everything-we-know-about-chatgpt
  • Yang, C., Huan, S., Yang, Y., 2020. A practical teaching mode for colleges supported by artificial intelligence. Int. J. Emerg. Technol. Learn....
  • Yeralan, S., Lee, L. A., 2023. Generative AI: Challenges to higher education. Sustainable Engineering and Innovation. DOI: 10.37868/sei.v5i2.id196...
  • Yi, Y., 2021. Uspostavljanje koncepta UI pismenosti: Focusing on competence and purpose. JAHR 12 (2), 353–368. DOI: 10.21860/j.12.2.8 DOI:...
  • Yin, Y., 2021. Research on ideological and political evaluation model of university students based on data mining artificial intelligence...
  • Yu, H., Guo, Y., Jun. 2023. Generative artificial intelligence empowers educational reform: current status, issues, and prospects. Frontiers...
  • Zhang, E., Shi, W., 2021. The construction of university teachers’ scientific research performance evaluation system under artificial intelligence....
  • Åström, K., Hägglund, T., Apr. 2000. Benchmark systems for pid control. IFAC Proceedings Volumes 33 (4), 165–166. DOI: 10.1016/s1474-6670(17)38238-1...