Publication:
Large scale summarization using ensemble prompts and in context learning approaches

Simple item page
dc.contributor.authorLeiva-Araos, Andrés
dc.contributor.authorGana, Bady
dc.contributor.authorAllende-Cid, Héctor
dc.contributor.authorGarcía, José
dc.contributor.authorJyoti Saikia, Manob
dc.date.accessioned2026-10-05T19:40:46Z
dc.date.available2026-10-05T19:40:46Z
dc.date.issued2025
dc.description.abstractThe field of Information Assurance (IA) and Cybersecurity has seen substantial evolution, driven by advancements in technology and the increasing sophistication of threats in the digital age. This study employs Large Language Models (LLMs), as well as other advanced NLP techniques, to conduct a comprehensive analysis of literature from 1967 to 2024. By analyzing a corpus of more than 62,000 documents extracted from Scopus, our approach involves a comprehensive methodology that includes two main phases: topic detection using BERTopic and automatic summarization with LLMs across various periods (annual and decades). By designing targeted queries to extract relevant papers, analyzing textual data, and applying advanced prompting techniques for summarization, we integrate computational models to handle large volumes of data. Our results demonstrate that an ensemble of methods (Ev2) outperforms traditional summarization and density-based approaches, with improvements ranging from 16.7% to 29.6% in keyword definition tasks. It generates summaries that outperform in 5 out of the 7 tested metrics while maintaining the logical integrity of bibliographic references. Our results illuminate the shifts in focus within Information Assurance across decades, revealing key breakthroughs and forecasting emerging areas of significance.
dc.description.versionVersión publicada
dc.format.extent21 p.
dc.identifier.citationLeiva-Araos, A., Gana, B., Allende-Cid, H. et al. Large scale summarization using ensemble prompts and in context learning approaches. Sci Rep 15, 10259 (2025). https://doi.org/10.1038/s41598-025-94551-8
dc.identifier.doihttps://doi.org/10.1038/s41598-025-94551-8
dc.identifier.urihttps://hdl.handle.net/11447/11223
dc.language.isoen
dc.subjectInformation assurance
dc.subjectCybersecurity trends
dc.subjectSystematic topic review
dc.subjectLarge language models
dc.subjectNatural language processing (NLP)
dc.subjectAutomatic summarization
dc.titleLarge scale summarization using ensemble prompts and in context learning approaches
dc.typeArticle
dcterms.accessRightsAcceso abierto
dcterms.sourceScientific Reports
dspace.entity.typePublication

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s41598-025-94551-8 (1).pdf
Size:
9.04 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
347 B
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Artículos Ingeniería

Implementado por OpenGeek Services