Más allá de la opacidad: marco conceptual de los modelos interpretables y enfoques de inteligencia artificial explicable (XAI)

Juan David Luján-Villar

doi:10.36105/stx.2026n17.02

Autores/as

Juan David Luján-Villar Secretaria de Educación del Distrito, Bogotá, Colombia https://orcid.org/0000-0001-8622-4774

DOI:

https://doi.org/10.36105/stx.2026n17.02

Palabras clave:

inteligencia artificial explicable, modelos interpretables, aprendizaje automático, transparencia

Resumen

Este trabajo propone la realización de una comparación entre modelos interpretables (interpretable models) y las técnicas de explicación (explanation techniques o XAI methods) en términos taxonómicos de demarcación conceptual. A través de un enfoque denominado desarrollo de marco conceptual (DMC), y la aplicación formal de un modelo de este campo, se ejemplifica el uso de esta tecnología disponible respecto al campo de las ciencias sociales y humanas. Los resultados evidencian un enorme potencial de esta área en la aplicación metodológica de estos enfoques en las ciencias sociales y humanas de vanguardia. Se concluye con la reflexión pertinente del aporte computacional de estas ideas sobre problemas complejos en términos de modelado, datos, evidencias y la transparencia necesaria de las dinámicas investigativas contemporáneas.

Descargas

Los datos de descarga aún no están disponibles.

Biografía del autor/a

Juan David Luján-Villar, Secretaria de Educación del Distrito, Bogotá, Colombia

Doctorando en Docencia y Educación Artística, Universidad de las Américas y el Caribe, UNAC (Colima,
México), Magister en Investigación Social Interdisciplinaria y Licenciado en Educación artística (UDFJC) (Bogotá, Colombia) y docente de la Secretaría de Educación del Distrito (Bogotá, Colombia).

Referencias

Aluvalu, R., Mehta, M., & Siarry, P. (2024). Explainable AI in health informatics. Springer Nature Singapore. https://doi.org/10.1007/978-981-97-3705-5 DOI: https://doi.org/10.1007/978-981-97-3705-5

Barredo, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities, and challenges toward responsible AI. Information Fusion, 58, 82-115. https://doi.org/10.1016/j.inffus.2019.12.012 DOI: https://doi.org/10.1016/j.inffus.2019.12.012

Chakraborty, D., Başağaoğlu, H., & Winterle, J. (2021). Interpretable vs. noninterpretable machine learning models for data-driven hydro-climatological process modeling. Expert Systems with Applications, 170, 114498. https://doi.org/10.1016/j.eswa.2020.114498 DOI: https://doi.org/10.1016/j.eswa.2020.114498

Dafali, S. M., Kissi, M., & El Beggar, O. (2023). Comparative study between global and local explainable models. En Kissi, M. & El Beggar, O. (2023). 2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA) (pp. 1-8). IEEE. https://doi.org/10.1109/sita60746.2023.10373599 DOI: https://doi.org/10.1109/SITA60746.2023.10373599

De, A., Saraf, S., Mishra, T.K., & Tripathy, B.K. (2024). Interpretation and visualization techniques in AI systems and applications. En Tripathy, B.K., & Seetha, H. (Eds.). (2024). Explainable, interpretable, and transparent AI systems (pp. 279-301). CRC Press. https://doi.org/10.1201/9781003442509 DOI: https://doi.org/10.1201/9781003442509-16

Dib, L., & Capus, L. (2025). Classifying XAI methods to resolve conceptual ambiguity. Technologies, 13(9), 390. https://doi.org/10.3390/technologies13090390 DOI: https://doi.org/10.3390/technologies13090390

Gaur, L., & Abraham, A. (Eds.). (2024). Role of explainable artificial intelligence in E-Commerce. Springer. https://doi.org/10.1007/978-3-031-55615-9 DOI: https://doi.org/10.1007/978-3-031-55615-9

Grobrügge, A., Mishra, N., Jakubik, J., & Satzger, G. (2024). Explainability in AI-Based Applications – A Framework for Comparing Different Techniques. En Fettke, P., Weigand, H., Frank, U., Huemer, C., & Schnellmann, M. (2024). 2024 26th International Conference on Business Informatics (CBI), Vienna, Austria, 2024 (pp. 70-79). https://doi.org/10.1109/cbi62504.2024.00018 DOI: https://doi.org/10.1109/CBI62504.2024.00018

Hofman, J.M., Watts, D.J., Athey, S., Garip, F., Griffiths, T.L., Kleinberg, J. & Yarkoni, T.(2021). Integrating explanation and prediction in computational social science. Nature, 595(7866), 181–188. https://doi.org/10.1038/s41586-021-03659-0 DOI: https://doi.org/10.1038/s41586-021-03659-0

Hsieh, W., Bi, Z., Jiang, C., Liu, J., Peng, B., Zhang, S., ... & Liu, M. (2024). A comprehensive guide to explainable AI: from classical models to LLMs. arXiv preprint. arXiv:2412.00800. https://doi.org/10.48550/arXiv.2412.00800

Huang, F., Jiang, S., Li, L., Zhang, Y., Zhang, Y., Zhang, R., Li, Q., Li, D., Shangguan, W., & Dai, Y. (2024). Applications of explainable artificial intelligence in earth system science. arXiv preprint. arXiv:2406.11882. https://doi.org/10.48550/arXiv.2406.11882

Jabareen, Y. (2009). Building a conceptual framework: Philosophy, definitions, and procedure. International Journal of Qualitative Methods, 8(4), 49–62. https://doi.org/10.1177/160940690900800406 DOI: https://doi.org/10.1177/160940690900800406

Jena, K. (2023). Innovations in Explainable AI: Bridging the Gap Between Complexity and Understanding. International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 9(6), 118-125. https://doi.org/10.32628/cseit2390613 DOI: https://doi.org/10.32628/CSEIT2390613

Joyce, D.W., Kormilitzin, A., Smith, K.A., & Cipriani, A. (2023). Explainable artificial intelligence for mental health through transparency and interpretability for understandability. Digital Medicine, 6(6). https://doi.org/10.1038/s41746-023-00751-9 DOI: https://doi.org/10.1038/s41746-023-00751-9

Juarez, J.M., Bielza, C., Fernandez-Llatas, C., Johnson, O., Kocbek, P., Larrañaga, P., Johnson, O., Štiglic, G., Martin, N., Munoz-Gama, G., Sepulveda, M., & Vellido, F. (2024). Explainable artificial intelligence and process mining applications for healthcare. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-54303-6 DOI: https://doi.org/10.1007/978-3-031-54303-6

Kalasampath, K., Spoorthi, K. N., Sajeev, S., Kuppa, S. S., Ajay, K., & Angulakshmi, M. (2025). A Literature review on applications of explainable artificial intelligence (XAI). IEEE Access, 13, 41111-41140. https://doi.org/10.1109/ACCESS.2025.3546681 DOI: https://doi.org/10.1109/ACCESS.2025.3546681

Khamparia, A., & Gupta, D. (Eds.). (2025). Explainable artificial intelligence for biomedical and healthcare applications. CRC Press. https://doi.org/10.1201/9781003220107 DOI: https://doi.org/10.1201/9781003220107

Kumar, A., Kumar, T.A., Das, P., Sharma, C., & Kumar, A. (2025). Explainable artificial intelligence in the healthcare industry. Scrivener Publishing, Wiley. https://doi.org/10.1002/9781394249312 DOI: https://doi.org/10.1002/9781394249312

Liu, Q., Gui, D., Zhang, L., Niu, J., Dai, H., Wei, G., & Hu, B.X., (2022). Simulation of regional groundwater levels in arid regions using interpretable machine learning models. Science of The Total Environment, 831, 154902. https://doi.org/10.1016/j.scitotenv.2022.154902 DOI: https://doi.org/10.1016/j.scitotenv.2022.154902

Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Del Ser, J., ... & Stumpf, S. (2024). Explainable artificial intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions. Information Fusion, 106, 102301. https://doi.org/10.1016/j.inffus.2024.102301 DOI: https://doi.org/10.1016/j.inffus.2024.102301

Luján-Villar, J.D. (2018). Ciencias sociales y sostenibilidad: tecnologías de investigación social aplicadas a lo urbano y lo rural. Revista de Antropología y Sociología: VIRAJES, 20(1), 61-81. https://doi.org/10.17151/rasv.2018.20.1.4 DOI: https://doi.org/10.17151/rasv.2018.20.1.4

Luján-Villar, J.D., & Luján-Villar, R.C. (2019). Complejidad y ciencia de sistemas: aproximación a su impacto actual en el mundo. CienciAmérica, 8(2), 103-122. https://doi.org/10.33210/ca.v8i2.234 DOI: https://doi.org/10.33210/ca.v8i2.234

Lundberg, S.M., & Lee, S.-I. (2018). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems (NeurIPS), 31, 4765–4774. https://doi.org/10.48550/arXiv.1705.07874

Malviya, R., & Sundram, S. (2025). Explainable and responsible artificial intelligence in healthcare. Scrivener Publishing, Wiley. https://doi.org/10.1002/9781394302444 DOI: https://doi.org/10.1002/9781394302444

Mathew, D.E., Ebem, D.U., Ikegwu, A.C. Eberechukwu, P., & Dibiaezue, N.F. (2025). Recent emerging techniques in explainable artificial intelligence to enhance the interpretable and understanding of AI models for human. Neural Processing Letters, 57(16), 1-32. https://doi.org/10.1007/s11063-025-11732-2 DOI: https://doi.org/10.1007/s11063-025-11732-2

Miller, T. (2019). Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267, 1-38. https://doi.org/10.1016/j.artint.2018.07.007 DOI: https://doi.org/10.1016/j.artint.2018.07.007

Molnar, C. (2022). Interpretable machine learning: A guide for making black-box models explainable.

https://christophm.github.io/interpretable-ml-book/

Murdoch, W.J., Singh, C., Kumbier, K., Abbasi-Asl, R., & Yu, B., (2019). Interpretable machine learning: definitions, methods, and applications. Proceedings of the National Academy of Sciences of the United States of America, 116, 22071–22080. https://doi.org/10.1073/pnas.1900654116 DOI: https://doi.org/10.1073/pnas.1900654116

Pretolesi, D., Stanzani, I., Ravera, S., Vian, A., Barla, A. (2025). Artificial intelligence and network science as tools to illustrate academic research evolution in interdisciplinary fields: The case of Italian design. PLOS ONE, 20(1), e0315216. https://doi.org/10.1371/journal.pone.0315216 DOI: https://doi.org/10.1371/journal.pone.0315216

Rehman, A., & Saba, T. (Eds.). (2025). Explainable artificial intelligence in medical imaging. Auerbach Publications, CRC Press. https://doi.org/10.1201/9781032626345 DOI: https://doi.org/10.1201/9781032626345

Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., & Zhong, C. (2022). Interpretable machine learning: Fundamental principles and 10 grand challenges. Statistic Surveys, 16, 1-85. https://doi.org/10.1214/21-SS133 DOI: https://doi.org/10.1214/21-SS133

Saarela, M., & Podgorelec, V. (2024). Recent applications of explainable AI (XAI): A systematic literature review. Applied Sciences, 14(19), 8884. https://doi.org/10.3390/app14198884 DOI: https://doi.org/10.3390/app14198884

Wang, Y. (2024). A comparative analysis of model agnostic techniques for explainable artificial intelligence. Research Reports on Computer Science, 3(2), 25-33. https://doi.org/10.37256/rrcs.3220244750 DOI: https://doi.org/10.37256/rrcs.3220244750

Whittemore, R., & Knafl, K. (2005). The integrative review: Updated methodology. Journal of

Advanced Nursing, 52(5), 546–553. https://doi.org/10.1111/j.1365-2648.2005.03621.x DOI: https://doi.org/10.1111/j.1365-2648.2005.03621.x

Zhang, Q., Ding, K., Lv, T., Wang, X., Yin, Q., Zhang, Y., ... & Chen, H. (2025). Scientific large language models: A survey on biological & chemical domains. ACM Computing Surveys, 57(6), 1-38. https://doi.org/10.1145/3715318 DOI: https://doi.org/10.1145/3715318