Large Language Models

An Overview of Large Language Model Approaches for Automated Software Vulnerability Detection

This article is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0)

In the modern world, software security has become a top priority, as it directly determines the reliability of digital solutions and user trust. The growing number of cyber threats and the increasing complexity of software systems highlight the necessity of using effective tools for control and vulnerability prevention.

Controlled Synthesis and Hierarchical Structuring of Ukrainian Datasets

The article addresses the urgent scientific and practical problem of overcoming the "cold start" effect in the development and deployment of Natural Language Processing (NLP) systems aimed at monitoring public opinion and sentiment analysis of Ukrainian-language content. The critical shortage of representative, balanced, and pre-labeled datasets that accurately reflect the specifics of social, economic, and political processes in modern Ukrainian society is identified as the main barrier to integrating advanced neural network solutions.

Using Large Language Model Tools to Conceptualise the Subject Area of DevOps

The study aims to justify and test an approach to the automated conceptualization of the DevOps subject area using large language models. This paper explores the potential applications of LLMs in concept classification, ontology construction, and configuration structure explanation. Additionally, it analyzes the models' capabilities in supporting the training and auditing of DevOps processes. The research methodology consists of four stages. First, an initial set of DevOps concepts was generated using an LLM.

NATURAL LANGUAGE–DRIVEN CHART SPECIFICATION AND GENERATION IN SUPERSET

Business intelligence dashboards provide powerful visualization capabilities, but creating diagrams typically requires manual configuration of visualization parameters, which limits accessibility for non-technical users. This paper presents a natural language interface for Superset that automatically generates visualization specifications from a user’s textual query.

AI-AGENT FOR WORKING WITH TOURISM BUSINESS

This paper is devoted to the development of an intelligent agent for automating user interaction with the web resources of tourism companies. An approach is proposed that combines prompt engineering techniques, contextual fine-tuning, and integration with web data through the n8n platform in order to obtain reliable information in real time. The core idea is to use the language model not only as a text generator, but also as a universal interpreter of HTML content and a semantic aggregator of data from the web resources of a tourism company.

Hybridizing Large Language Models and Markov Processes: a New Paradigm for Autonomous Penetration Testing

The article explores a hybrid framework for autonomous penetration testing that integrates Large Language Models (LLMs) with Markov decision processes (MDP/POMDP) and reinforcement learning (RL). Conventional penetration testing is increasingly insufficient for modern, complex cyber threats. LLMs are utilized for high-level strategic planning, generating potential attack paths, while MDP/POMDP models combined with RL execute low-level actions under uncertainty. A feedback loop allows outcomes to refine strategies in dynamic and partially observable environments.

Information Technology for Text Classification Tasks Using Large Language Models

The article addresses the problem of text classification in the context of growing information flows and the need for automated content analysis. A universal information technology is proposed, combining classical machine learning methods with the potential of Large Language Models for processing news, scientific, literary, journalistic and legal texts. Using the BBC News corpus (2225 texts), k-means clustering with TF-IDF demonstrated clear thematic grouping.

RESEARCH OF THE ORGANIC TRAFFIC OPTIMIZATION SYSTEM FOR E-COMMERCE PLATFORMS USING LARGE LANGUAGE MODELS

The paper explores the use of large language models (LLM) to optimize SEO processes to increase organic traffic for e-commerce platforms. The possibilities of scalable adaptation of large content volumes to the requirements of search algorithms using tools built on the basis of LLM are considered. A comparative analysis of the effectiveness of new automated SEO optimization methods and traditional manual tuning approaches is conducted using the example of an e-commerce platform with a wide range of products and a high level of traffic.