Large scale summarization using ensemble prompts and in context learning approaches
Open Access
- 25 March 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-21
Abstract
The 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.Keywords
This publication has 26 references indexed in Scilit:
- A survey on large language model (LLM) security and privacy: The Good, The Bad, and The UglyHigh-Confidence Computing, 2024
- A Systematic Review on Intrusion Detection System in Wireless Networks: Variants, Attacks, and ApplicationsWireless Personal Communications, 2023
- SecureBERT: A Domain-Specific Language Model for Cybersecurity2023
- A Systematic Literature Review on Phishing Email Detection Using Natural Language Processing TechniquesIEEE Access, 2022
- AI-Driven Cybersecurity: An Overview, Security Intelligence Modeling and Research DirectionsSN Computer Science, 2021
- Aspect-Based Text Summarization Using MapReduce Optimization2018
- Summarization using mapreduce framework based big data and hybrid algorithm (HMM and DBSCAN)2017
- Density-Based Clustering Based on Hierarchical Density Estimates2013
- The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem SolutionsInternational Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 1998
- A generalized Kruskal-Wallis test for comparing K samples subject to unequal patterns of censorshipBiometrika, 1970