Simplificación y reelaboración asistida con LLM
un enfoque modular basado en prompting para la comprensión de textos expositivos
DOI:
https://doi.org/10.59471/raia2026236Palabras clave:
simplificación textual, ingeniería de prompts, comprensión lectora, nominalización, modelos de lenguaje generativosResumen
La comprensión de textos expositivos académicos constituye un desafío persistente en el ámbito universitario, en parte debido a rasgos como la alta densidad informacional, la complejidad sintáctica y estructuras lingüísticas abstractas —nominalizaciones, construcciones impersonales—. A partir de aportes de la psicología cognitiva y la psicolingüística, este trabajo sostiene que la dificultad de los textos no reside únicamente en su complejidad conceptual, sino en la forma en que ese contenido se codifica lingüísticamente: las estructuras agente-acción-objeto, alineadas con el orden de los eventos, facilitan el procesamiento, mientras que las nominalizaciones, la voz pasiva y la sintaxis densa incrementan la carga inferencial, especialmente en lectores novatos. Retomando marcos recientes de caracterización del prompting en contextos académicos, se propone un protocolo modular de simplificación asistida mediante modelos de lenguaje generativos. El protocolo comprende cinco módulos de transformación —desnominalización de procesos, explicitación de agentes, segmentación sintáctica, explicitación relacional e integración de ejemplos disciplinares— y un módulo transversal de metacomprensión que visibiliza las transformaciones realizadas. Cada módulo se organiza en torno a un fundamento teórico, un rasgo objetivo, una regla de transformación, criterios de control y una instrucción operativa. Se ilustra la aplicación mediante cuatro casos disciplinares (sociología, biología, economía, derecho). El enfoque distingue complejidad conceptual de complejidad discursiva, ofreciendo una alternativa sistemática y flexible a la simplificación automática tradicional. Entre las limitaciones se destaca la ausencia de validación empírica con usuarios, señalada como línea prioritaria de investigación futura.
Descargas
Referencias
Arnold, J. E., Losongco, A., Wasow, T., & Ginstrom, R. (2000). Heaviness vs. newness: The effects of structural complexity and discourse status on constituent ordering. Language, 76(1), 28-55. https://doi.org/10.2307/417392
Barnett, S. M., & Ceci, S. J. (2002). When and where do we apply what we learn?: A taxonomy for far transfer. Psychological Bulletin, 128(4), Article 4. https://doi.org/10.1037/0033-2909.128.4.612
Barsalou, L. W. (2008). Grounded Cognition. Annual Review of Psychology, 59(1), 617-645. https://doi.org/10.1146/annurev.psych.59.103006.093639
Barsalou, L. W. (2010). Grounded Cognition: Past, Present, and Future: Topics in Cognitive Science. Topics in Cognitive Science, 2(4), 716-724. https://doi.org/10.1111/j.1756-8765.2010.01115.x
Behaghel, O. (1936). ’Deutsche Syntax: Eine geschichtliche Darstellung. 4, Wortstellung, Periodenbau’—Details | MDZ. https://www.digitale-sammlungen.de/en/details/bsb11023511
Bernardo, A. B. I. (2001). Analogical Problem Construction and Transfer in Mathematical Problem Solving. Educational Psychology, 21(2), Article 2. https://doi.org/10.1080/01443410020043841
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., Brynjolfsson, E., Buch, S., Card, D., Castellon, R., Chatterji, N., Chen, A., Creel, K., Davis, J. Q., Demszky, D., … Liang, P. (2021, agosto 16). On the Opportunities and Risks of Foundation Models. arXiv.Org. https://arxiv.org/abs/2108.07258v3
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., … Amodei, D. (2020). Language Models are Few-Shot Learners (arXiv:2005.14165). arXiv. https://doi.org/10.48550/arXiv.2005.14165
Catrambone, R., & Holyoak, K. J. (1989). Overcoming contextual limitations on problem-solving transfer. Journal of Experimental Psychology: Learning, Memory, and Cognition, 15(6), Article 6. https://doi.org/10.1037/0278-7393.15.6.1147
Chi, M., Feltovich, P. J., & Glaser, R. (1981). Categorization and representation of physics problems by experts and novices. Cognitive science, 5(2), Article 2.
Cisneros, L. (2012). La reducción inevitable: Sobre la definición en el discurso académico. En Retóricas del decir. Lenguaje, verdad y creencia en la escritura académica. FHUMYAR Ediciones, Facultad de Humanidades y Artes - UNR.
Clark, H. H., & Clark, E. V. (1977). Psychology and Language: An Introduction to Psycholinguistics.
D’Angelo, V. S., & Trench, M. (2022). Defending Diversity: Providing Examples from Different Domains Enhances Application of System Principles Beyond the Domains Covered by the Examples. Proceedings of the Annual Meeting of the Cognitive Science Society, 44(44), Article 44. https://escholarship.org/uc/item/85k6f518
D’Angelo, V., & Trench, J. M. (2024). Aprendizaje de conceptos abstractos en estudiantes que emplean el Español como segunda lengua: Efectos de la complejidad de las definiciones. Revista Argentina de Ciencias del Comportamiento ( RACC ), 16(Extra 3 (Suplemento (Septiembre))), 224-225.
D’Angelo, V., & Trench, M. (2020). Enhancing distant analogical retrieval via generating abstract redescriptions of the target. Paper presented at the Conceptual Abstraction and Analogy in Natural and Artificial Systems Symposium of the Association for the Advancement of Artificial Intelligence, Washington, DC.
Gentner, D. (1983). Structure-mapping: A theoretical framework for analogy. Cognitive Science, 7(2), Article 2. https://doi.org/10.1016/S0364-0213(83)80009-3
Goldwater, M. B., & Gentner, D. (2015). On the acquisition of abstract knowledge: Structural alignment and explication in learning causal system categories. Cognition, 137, 137-153. https://doi.org/10.1016/j.cognition.2014.12.001
Goldwater, M. B., & Schalk, L. (2016). Relational categories as a bridge between cognitive and educational research. Psychological Bulletin, 142(7), Article 7.
Guisen, M. A., Giorgi, L. N., Serra, L. L., & Acosta, P. E. (2025). Taxonomía de prompts para optimizar la accesibilidad académica en sistemas de Inteligencia Artificial conversacional. Revista Abierta de Informática Aplicada, 9(1), 36-51. https://doi.org/10.59471/raia2025216
Hackemann, T., Heine, L., & Höttecke, D. (2022). Challenging to Read, Easy to Comprehend? Effects of Linguistic Demands on Secondary Students’ Text Comprehension in Physics. International Journal of Science and Mathematics Education, 20(1), 43-68. https://doi.org/10.1007/s10763-022-10306-1
Hazzan, O. (1999). Reducing abstraction level when learning abstract algebra concepts. Educational Studies in Mathematics, 40(1), Article 1.
Hazzan, O. (2003). How students attempt to reduce abstraction in the learning of mathematics and in the learning of computer science. Computer Science Education, 13(2), Article 2.
Hunsu, N. J., Adesope, O., & McCrudden, M. T. (2023). The effects of text structure on students’ use of comprehension strategies and cognitive outcomes during science text processing. Frontiers in Education, 8. https://doi.org/10.3389/feduc.2023.1112804
Kendeou, P., McMaster, K. L., & Christ, T. J. (2016). Reading Comprehension: Core Components and Processes. Policy Insights from the Behavioral and Brain Sciences, 3(1), 62-69. https://doi.org/10.1177/2372732215624707
Kendeou, P., van den Broek, P., Helder, A., & Karlsson, J. (2014). A Cognitive View of Reading Comprehension: Implications for Reading Difficulties. Learning Disabilities Research & Practice, 29(1), 10-16. https://doi.org/10.1111/ldrp.12025
Kintsch, W. (1998). Comprehension: A paradigm for cognition. Cambridge university press.
Lakoff, G. (2024). Women, Fire, and Dangerous Things: What Categories Reveal about the Mind. University of Chicago Press. (Obra original publicada en 1987)
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023). Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing. ACM Comput. Surv., 55(9), 195:1-195:35. https://doi.org/10.1145/3560815
Mandler, J. M., & Orlich, F. (1993). Analogical transfer: The roles of schema abstraction and awareness. Bulletin of the Psychonomic Society, 31(5), Article 5.
McMaster, K. L., & Kendeou, P. (2023). Refocusing reading comprehension: Aligning theory with assessment and intervention. Learning and Individual Differences, 102, 1-3. https://doi.org/10.1016/j.lindif.2023.102256
McNamara, D. S. (2001). Reading both high-coherence and low-coherence texts: Effects of text sequence and prior knowledge. Canadian Journal of Experimental Psychology / Revue canadienne de psychologie expérimentale, 55(1), 51-62. https://doi.org/10.1037/h0087352
McNamara, D. S., Kintsch, E., Songer, N. B., & Kintsch, W. (1996). Are good texts always better? Interactions of text coherence, background knowledge, and levels of understanding in learning from text. Cognition and Instruction, 14(1), 1-43. https://doi.org/10.1207/s1532690xci1401_1
McNamara, D. S., & Kintsch, W. (1996). Learning from texts: Effects of prior knowledge and text coherence. Discourse Processes, 22(3), 247-288. https://doi.org/10.1080/01638539609544975
Murphy, G. (2002). The big book of concepts. MIT press.
Paivio, A. (1990). Mental representations: A dual coding approach. Oxford university press.
Rawson, K. A., Thomas, R. C., & Jacoby, L. L. (2015). The Power of Examples: Illustrative Examples Enhance Conceptual Learning of Declarative Concepts. Educational Psychology Review, 27(3), Article 3. https://doi.org/10.1007/s10648-014-9273-3
Saggion, H. (2017). Automatic Text Simplification. Springer International Publishing. https://doi.org/10.1007/978-3-031-02166-4
Schulhoff, S., Ilie, M., Balepur, N., Kahadze, K., Liu, A., Si, C., Li, Y., Gupta, A., Han, H., Schulhoff, S., Dulepet, P. S., Vidyadhara, S., Ki, D., Agrawal, S., Pham, C., Kroiz, G., Li, F., Tao, H., Srivastava, A., … Resnik, P. (2024, junio 6). The Prompt Report: A Systematic Survey of Prompt Engineering Techniques. arXiv.Org. https://arxiv.org/abs/2406.06608v6
Shardlow, M. (2014). A Survey of Automated Text Simplification. International Journal of Advanced Computer Science and Applications, 4. https://doi.org/10.14569/SpecialIssue.2014.040109
Siddharthan, A. (2014). A survey of research on text simplification. ITL - International Journal of Applied Linguistics, 165(2), 259-298. https://doi.org/10.1075/itl.165.2.06sid
Specia, L., Jauhar, S. K., & Mihalcea, R. (2012). SemEval-2012 Task 1: English Lexical Simplification. En E. Agirre, J. Bos, M. Diab, S. Manandhar, Y. Marton, & D. Yuret (Eds.), *SEM 2012: The First Joint Conference on Lexical and Computational Semantics – Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation (SemEval 2012) (pp. 347-355). Association for Computational Linguistics. https://aclanthology.org/S12-1046/
Tong, X., Yu, L., Li, H., Liu, D., & Deacon, S. H. (2026). The influence of text complexity on the relationship between syntactic awareness and reading comprehension. Learning and Individual Differences, 126, 102864. https://doi.org/10.1016/j.lindif.2025.102864
Trench, J. M., Rivas, L., & Minervino, R. (s. f.). Transfer-Appropriate Generalization. en revisión.
Wasow, T. (2001). Postverbal Behavior. http://web.stanford.edu/group/cslipublications/cslipublicationspdf/1575864029.pdf
Wissman, K. T., Zamary, A., Rawson, K. A., & Dunlosky, J. (2023). Enhancing declarative concept application: The utility of examples as primary targets of learning. Journal of Experimental Psychology: Applied, 29(2), Article 2. https://doi.org/10.1037/xap0000432
Xu, W., Callison-Burch, C., & Napoles, C. (2015). Problems in Current Text Simplification Research: New Data Can Help. Transactions of the Association for Computational Linguistics, 3, 283-297. https://doi.org/10.1162/tacl_a_00139
Zamary, A. S. (2019). Evaluating the Dual-Route and Recruitment Hypotheses: Utilizing Both Definitions and Examples for Supporting Declarative Concept Application [Kent State University]. https://etd.ohiolink.edu/apexprod/rws_olink/r/1501/10?clear=10&p10_accession_num=kent1562924203406036
Publicado
Número
Sección
Licencia

Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
