Generación de reportes descriptivos usando inteligencia artificial generativa: Un mapeo sistemático
Palabras clave:
LLM, XAI, RAG, Reportes, Toma de DecisionesBarra lateral del artículo
Contenido principal del artículo
Introducción: Los modelos de lenguaje de gran tamaño (LLMs) han incrementado su uso entre científicos, estudiantes y docentes como herramientas de apoyo en actividades cotidianas.
Objetivo: Analizar el uso de tecnologías emergentes, como los LLMs, en la toma de decisiones a partir de conocimiento previamente procesado y extender el uso de generación de reportes descriptivos.
Metodología: Se realizó un mapeo sistemático que permitió identificar brechas y oportunidades en el uso de estos modelos.
Resultados: Los resultados evidencian que la mayoría de los autores proponen la gestión del conocimiento mediante enfoques como la generación aumentada por recuperación (RAG) y la inteligencia artificial explicable (XAI), con el fin de garantizar la fiabilidad de los textos generados. En la literatura se reporta el uso de modelos como ChatGPT-4, Llama y Gemini 2, destacando su evolución y capacidades en procesamiento de lenguaje natural.
Conclusiones: Aún existen barreras en el uso adecuado de los LLMs, por lo que se requieren investigaciones futuras orientadas a fortalecer la robustez y confiabilidad de los modelos en la generación de informes para la toma de decisiones.
1. Lu Y, Aleta A, Du C, Shi L, Moreno Y. LLMs and generative agent-based models for complex systems research. Phys Life Rev. 2024;51:283-93.
https://doi.org/10.1016/j.plrev.2024.10.013
2. Izacard G, Grave E. Distilling Knowledge from Reader to Retriever for Question Answering. arXiv preprint arXiv:2012.04584 [Internet]. International Conference on Learning Representations, ICLR; 2022. Available from: http://arxiv.org/abs/2012.04584
3. Malhotra A, Jindal R. XAI Transformer based Approach for Interpreting Depressed and Suicidal User Behavior on Online Social Networks. Cogn Syst Res. 2024;84:101186.
https://doi.org/10.1016/j.cogsys.2023.101186
4. Mersha MA, Yigezu MG, Kalita J. Evaluating the effectiveness of XAI techniques for encoder-based language models. Knowl Based Syst. 2025;310:113042.
https://doi.org/10.1016/j.knosys.2025.113042
5. Zohuri B, Behgounia F. Application of artificial intelligence driving nano-based drug delivery system. In: A Handbook of Artificial Intelligence in Drug Delivery [Internet]. Elsevier; 2023 [cited 2025 Sep 13]. p. 145-212.
https://doi.org/10.1016/B978-0-323-89925-3.00007-1
6. Campo Yule JE, Díaz Mage D alberto, Ordoñez HA. Técnicas de Machine Learning aplicadas al consumo de sustancias psicoactivas ilícitas: Un mapeo sistémico. Inge CuC. 2023;19(2):4.
https://doi.org/10.17981/ingecuc.19.2.2023.08
7. Petersen K, Vakkalanka S, Kuzniarz L. Guidelines for conducting systematic mapping studies in software engineering: An update. Inf Softw Technol. 2015;64:1-18.
https://doi.org/10.1016/j.infsof.2015.03.007
8. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;n71.
https://doi.org/10.1136/bmj.n71
9. Lin B. Reinforcement learning and bandits for speech and language processing: Tutorial, review and outlook. Expert Syst Appl. 2024;238:122254.
https://doi.org/10.1016/j.eswa.2023.122254
10. Zhou J, Li X, Xia Q, Yu L. Innovations in otolaryngology using LLM for early detection of sleep-disordered breathing. SLAS Technol. 2025;32:100278.
https://doi.org/10.1016/j.slast.2025.100278
11. Ravaut M, Zhao R, Phung D, Qin VM, Milovanovic D, Pienkowska A, et al. Targeting COVID-19 and Human Resources for Health News Information Extraction: Algorithm Development and Validation. JMIR AI. 2024;3:e55059.
12. Yu D. Towards LLM-assisted move annotation: Leveraging ChatGPT-4 to analyse the genre structure of CEO statements in corporate social responsibility reports. English for Specific Purposes. 2025;78:33-49.
https://doi.org/10.1016/j.esp.2024.11.003
13. Kovari A. Explainable AI chatbots towards XAI ChatGPT: A review. Heliyon. 2025;11(2):e42077.
https://doi.org/10.1016/j.heliyon.2025.e42077
14. Tizaoui T, Tan R. Towards a benchmark dataset for large language models in the context of process automation. Digital Chemical Engineering. 2024;13:100186.
https://doi.org/10.1016/j.dche.2024.100186
15. Arslan M, Munawar S, Cruz C. Political Events using RAG with LLMs. Procedia Comput Sci. 2024;246:5027-35.
https://doi.org/10.1016/j.procs.2024.09.576
16. Rique T, Perkusich M, Gorgônio K, Almeida H, Perkusich A. Constructing the graphical structure of expert-based Bayesian networks in the context of software engineering: A systematic mapping study. Inf Softw Technol. 2025;177:107586.
https://doi.org/10.1016/j.infsof.2024.107586
17. Chakraborty C, Bhattacharya M, Pal S, Chatterjee S, Das A, Lee SS. AI-enabled language models (LMs) to large language models (LLMs) and multimodal large language models (MLLMs) in drug discovery and development. J Adv Res. 2025;78:377-89.
https://doi.org/10.1016/j.jare.2025.02.011
18. Thomas J, Mudgal A, Liu W, Tahiraj N, Mohammed Z, Diddi D. Preserving Privacy, Increasing Accessibility, and Reducing Cost: An On-Device Artificial Intelligence Model for Medical Transcription and Note Generation.
https://doi.org/10.1101/2025.07.01.25330679
19. Yan B, Li K, Xu M, Dong Y, Zhang Y, Ren Z, et al. On protecting the data privacy of Large Language Models (LLMs) and LLM agents: A literature review. High-Confidence Computing. 2025;100300.
https://doi.org/10.1016/j.hcc.2025.100300
20. Ferrag MA, Alwahedi F, Battah A, Cherif B, Mechri A, Tihanyi N, et al. Generative AI in Cybersecurity: A Comprehensive Review of LLM Applications and Vulnerabilities. Internet of Things and Cyber-Physical Systems. 2025;5:1-46.
https://doi.org/10.1016/j.iotcps.2025.01.001
21. Adam D, Kliegr T. Traceable LLM-based validation of statements in knowledge graphs. Inf Process Manag. 2025;62(4):104128.
https://doi.org/10.1016/j.ipm.2025.104128
22. Nakamura M, Hayamizu S, Masanori H, Fuseya T, Iwamatsu H, Terada K. Causal Reasoning of Occupational Incident Texts Using Large Language Models. Procedia Comput Sci. 2024;246:820-9.
https://doi.org/10.1016/j.procs.2024.09.501
23. Zou Y, Shi M, Chen Z, Deng Z, Lei Z, Zeng Z, et al. ESGReveal: An LLM-based approach for extracting structured data from ESG reports. J Clean Prod. 2025;489:144572.
https://doi.org/10.1016/j.jclepro.2024.144572
24. Pagano S, Strumolo L, Michalk K, Schiegl J, Pulido LC, Reinhard J, et al. Evaluating ChatGPT, Gemini and other Large Language Models (LLMs) in orthopaedic diagnostics: A prospective clinical study. Comput Struct Biotechnol J. 2025;28:9-15.
https://doi.org/10.1016/j.csbj.2024.12.013
25. Arslan M, Mahdjoubi L, Munawar S. Driving sustainable energy transitions with a multi-source RAG-LLM system. Energy Build. 2024;324:114827.
https://doi.org/10.1016/j.enbuild.2024.114827
26. Jain T, Gao Y, Vanga S, Singla K. News Reporter: A Multi-lingual LLM Framework for Broadcast TV News. arXiv preprint arXiv:2410.07520 [Internet]. 2024. Available from: https://arxiv.org/pdf/2410.07520
27. Tonouchi Y, Nakai S, Nurakami K, Kataoka Y. Effectiveness of a Large Language Model-Based Feedback System for Case Report Writing in Novice Rehabilitation Staff Education: A Mixed-Methods Study. Rehabilitation [Internet]. Jxiv preprint; 2024. Available from: https://jxiv.jst.go.jp/index.php/jxiv/preprint/download/844/2450/2296
28. Sacoransky E, Kwan BYM, Soboleski D. ChatGPT and assistive AI in structured radiology reporting: A systematic review. Curr Probl Diagn Radiol. 2024;53(6):728-37.
https://doi.org/10.1067/j.cpradiol.2024.07.007
29. Scanlon M, Breitinger F, Hargreaves C, Hilgert JN, Sheppard J. ChatGPT for digital forensic investigation: The good, the bad, and the unknown. Forensic Science International: Digital Investigation. 2023;46:301609.
https://doi.org/10.1016/j.fsidi.2023.301609
30. Gmeiner F, Yildirim N. Dimensions for Designing LLM-based Writing Support. In: In2Writing Workshop at CHI [Internet]. Hamburg, Germany: Association for Computing Machinery (ACM); 2023 [cited 2026 May 3]. Available from: https://www.frederic-otto.com/papers/DimensionsforDesigningLLM-basedWritingSupport.pdf
31. Hatem S, Khoriba G, Gad-Elrab MH, ElHelw M. Up To Date: Automatic Updating Knowledge Graphs Using LLMs. Procedia Comput Sci. 2024;244:327-34.
https://doi.org/10.1016/j.procs.2024.10.206
32. Jiang G, Shi X, Luo Q. Llm-collaboration on automatic science journalism for the general audience. arXiv preprint arXiv:2407.09756. 2024.
https://doi.org/10.48550/arXiv.2407.09756
33. Cruz-Castro L, Castelblanco G, Antonenko P. LLM-based system for technical writing real-time review in urban construction and technology. Proceedings of 60th Annual Associated Schools. 2024;5:130-8.
34. Chakrabarty T, Laban P, Wu CS. Can AI writing be salvaged? Mitigating Idiosyncrasies and Improving Human-AI Alignment in the Writing Process through Edits. arXiv preprint arXiv:2409.14509 [Internet]. 2024. Available from:
https://doi.org/10.1145/3706598.3713559
35. Mazzone S, Harlan J, Xu LZ, Ow T. LLMs Enhance Emotional Expression While Maintaining Analytical Depth in News Writing. In: Scholar Space [Internet]. 2025.
https://doi.org/10.24251/HICSS.2025.278
36. Soós D. Who Wrote the Scientific News? Improving the Discernibility of LLMs to Human-Written Scientific News. Old Dominion University; 2024.
https://digitalcommons.odu.edu/computerscience_etds/178
37. Zheng L, Jiang F, Gu X, Li Y, Wang G, Zhang H. Teaching via LLM-enhanced simulations: Authenticity and barriers to suspension of disbelief. Internet High Educ. 2025;65:100990.
https://doi.org/10.1016/j.iheduc.2024.100990
38. Zhang H, Yan W, Hu H, Zhang X, Liu Q, Xia H, et al. An LLM-based knowledge and function-augmented approach for optimal design of remanufacturing process. Advanced Engineering Informatics. 2025;65:103206.
https://doi.org/10.1016/j.aei.2025.103206
39. Longo L, Brcic M, Cabitza F, Choi J, Confalonieri R, Ser J Del, et al. Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions. Information Fusion. 2024;106:102301.
https://doi.org/10.1016/j.inffus.2024.102301
40. Haurogné J, Basheer N, Islam S. Vulnerability detection using BERT based LLM model with transparency obligation practice towards trustworthy AI. Machine Learning with Applications. 2024;18:100598.
https://doi.org/10.1016/j.mlwa.2024.100598
41. Brandsæter A, Glad IK. XAI in hindsight: Shapley values for explaining prediction accuracy. Expert Syst Appl. 2025;273:126845.
https://doi.org/10.1016/j.eswa.2025.126845
42. Weber L, Lapuschkin S, Binder A, Samek W. Beyond explaining: Opportunities and challenges of XAI-based model improvement. Information Fusion. 2023;92:154-76.
https://doi.org/10.1016/j.inffus.2022.11.013
43. Jouis G, Mouchère H, Picarougne F, Hardouin A. A methodology to compare XAI explanations on natural language processing. In: Benois-Pineau J, Bourqui R, Petkovic D, Quénot G, editors. Explainable Deep Learning AI [Internet]. Imprint Academic Press (libro 2023): Elsevier; 2023. p. 191-216.
https://doi.org/10.1016/B978-0-32-396098-4.00016-8
44. Martens D, Hinns J, Dams C, Vergouwen M, Evgeniou T. Tell me a story! Narrative-driven XAI with Large Language Models. Decis Support Syst. 2025;191:114402.
https://doi.org/10.1016/j.dss.2025.114402
45. Shimizu I, Kasai H, Shikino K, Araki N, Takahashi Z, Onodera M, et al. Developing Medical Education Curriculum Reform Strategies to Address the Impact of Generative AI: Qualitative Study. JMIR Med Educ. 2023;9.
46. Erickson JS, Santos H, Pinheiro V, McCusker JP, McGuinness DL. LLM experimentation through knowledge graphs: Towards improved management, repeatability, and verification. J Web Semant. 2025;85:100853.
https://doi.org/10.1016/j.websem.2024.100853
47. Perera Molligoda Arachchige AS. Empowering radiology: the transformative role of ChatGPT. Clin Radiol. 2023;78(11):851-5.
https://doi.org/10.1016/j.crad.2023.08.006
48. Sarbaree Mishra. The age of explainable AI: improving trust and transparency in AI models. International Journal of Artificial Intelligence, Data Science, and Machine Learning. 2020;1.
https://doi.org/10.63282/3050-9262.IJAIDSML-V1I4P105
49. Chan PYP, Keung J, Yang Z. Effectiveness of symmetric metamorphic relations on validating the stability of code generation LLM. Journal of Systems and Software. 2025;222:112330.
https://doi.org/10.1016/j.jss.2024.112330
50. Xu Z, Song T, Lee YC. Confronting verbalized uncertainty: Understanding how LLM’s verbalized uncertainty influences users in AI-assisted decision-making. Int J Hum Comput Stud. 2025;197:103455.
https://doi.org/10.1016/j.ijhcs.2025.103455
51. Rapp A, Di Lodovico C, Di Caro L. How do people react to ChatGPT’s unpredictable behavior? Anthropomorphism, uncanniness, and fear of AI: A qualitative study on individuals’ perceptions and understandings of LLMs’ nonsensical hallucinations. Int J Hum Comput Stud. 2025;198:103471.
https://doi.org/10.1016/j.ijhcs.2025.103471
52. Vincent S, Wang P, Shi Z, Koka S, Fang Y. Measuring Large Language Models Capacity to Annotate Journalistic Sourcing.
https://doi.org/10.48550/arXiv.2501.00164
53. Dibia V. LIDA: A tool for automatic generation of grammar-agnostic visualizations and infographics using large language models. 2023
Downloads
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
Los autores que publican en esta revista están de acuerdo con los siguientes términos:
Los autores ceden los derechos patrimoniales a la revista y a la Universidad del Valle sobre los manuscritos aceptados, pero podrán hacer los reusos que consideren pertinentes por motivos profesionales, educativos, académicos o científicos, de acuerdo con los términos de la licencia que otorga la revista a todos sus artículos.
Los artículos serán publicados bajo la licencia Creative Commons 4.0 BY-NC-SA (de atribución, no comercial, sin obras derivadas).