The development of a recommendation module for a system for selecting measures in hazardous natural situations is described. An overview of software products aimed at developing adaptation measures to climate risks is provided. A review of methods for automating text classification, document processing, and data structuring is conducted. A multi-agent approach is proposed for the development of the module. The architecture and functional capabilities of the system's agents are described. Their performance is evaluated, and methods for improving the quality of query classification to increase it are used. Large language model technology is used for automatic text analysis. The knowledge base includes 210 case studies from 12 countries, covering situations such as droughts, floods, and heat waves, as well as corresponding adaptation measures such as constructing drainage systems and introducing drought-resistant crops. A user interface for interacting with the agents has been developed. An example of how recommendations are generated is provided.
This article is about the development of a fuzzy cognitive map using a local large language model, and the model is thoroughly tested; Qwen2.5-32B is used and the data is extracted from hotel reviews from TripAdvisor and a fuzzy cognitive map is trained and evaluated.
The rapid proliferation of unstructured data on digital platforms has generated an urgent demand for intelligent systems that can extract meaningful knowledge and produce accurate predictions. This study presents an automated knowledge extraction and prediction system using the advancements in Artificial Intelligence (AI) tools, which is referred to as APEX-LLM. The proposed system uses the latest architectures based on transformers for processing massive textual data, mining relevant entities, relationships, and patterns, and structuring them into knowledge-based representations. The framework integrates knowledge retrieval, natural language understanding, and machine learning techniques for immediate retrieval of knowledge from other sources such as documents, web content and databases. Furthermore, there is an integration of elements related to predictive modelling to analyze the knowledge extracted and predict trends, outcomes, or an action in various regions. It is a scalable, domain-independent system which can be customized and applied to health, financial and business sectors, and education. The experimental analysis demonstrates that the proposed method is much more accurate and efficient than the traditional rule-based and statistical methods. The results demonstrate that the LLM-based system has an overall automation rate of 99.2%, which is significantly higher than the 90.7% for rule-based and 83.9% for statistical methods, thereby minimizing the human factor by 99.6% and enhancing the accuracy of decision-making to 99.4%. This APEX-LLM will be added to the emerging branch of AI-enabled knowledge systems, offering a single solution for extraction and prediction tasks.
A fundamental change in information retrieving (IR) has been brought about by the quick development of large language patterns (LLMs), which go beyond standard keyword inquiries and ranked outcome lists. Retrieving-Augmented Generation that followed, a more interactive and lively regaining process that incorporates different facets of Accessibility to data into the conversation amongst an individual and the internet engines for searching and exploring, is one of the new interaction forms introduced by LLMs, which are now crucial to the development of IR technologies. We examine the complex effects of LLMs on IR, focusing on three different layers from which they have become essential to the retrieving process: the interaction layer, the structure for obtaining information and a computation pipeline functionality that can leverage a richer meaning representation through sophisticated language patterns, as well as the larger IR ecology. This work introduces a trust based adaptive reranking model- ATM (Adaptive Trust Model)that allocates computational resources according to file level uncertainty. Instead of assigning a fixed number of reranker calls per query, ATM focuses computation only where ranking confidence is low. This concentrate on prejudice, fairness, and ethical considerations in addition to evaluation challenges for the latter. The model gives 15–30% reduction in floating point operations (FLOPs) and up to 20% lower latency while maintaining or improving retrieval precision. To illustrate the influence on one area of study, we point to a few current examples of LLMs being employed in the medical field
Jenny Kalaiarasi.S· Journal of Intelligent Decis...· 0 citations
Influence diagrams address the challenges of decision-making under risk by structuring information, decisions and values, while clearly depicting uncertainties and probabilistic dependencies. However, constructing an influence diagram requires expertise in decision analysis and is further complicated by the need to process large amounts of contextual information. This work focuses on the construction of influence diagrams from natural language input by leveraging large language models (LLMs). We design a workflow that prompts LLMs to output elements of an influence diagram and resolves issues through verification and regeneration. We also construct a new dataset of typical decision problems under risk. Evaluations using this dataset demonstrate that our framework effectively identifies key factors and relationships in natural language, making better decisions than standalone LLMs and LLMs enhanced with standard techniques such as chain-of-thought (CoT). Finally, we apply LAMDA to discussions by groups of disease control experts on a hypothetical pandemic to demonstrate its real-world applicability. Overall, the method effectively synthesizes unstructured text into an influence diagram that, while subject to human review and refinement, enhances information processing and supports decision-making.
Voluntary safety reports provide valuable information for identifying potential risks and improving safety management in civil aviation. However, these reports are often large in volume, unstructured in format, and rich in domain-specific terminology, making manual analysis costly, inefficient, and difficult to scale. To address these challenges, this paper proposes TMCAS, an efficient large language model-assisted topic modeling framework for civil aviation safety reports. The proposed framework combines domain-adapted text embeddings, density-based clustering, representative sampling, noise repair, and large language model-based topic generation. Specifically, a contrastive learning-based fine-tuning strategy is introduced to enhance the semantic representation of aviation safety texts. An HDBSCAN-based clustering and sampling mechanism is then designed to select representative reports and reduce the computational cost of large language model inference, while a noise-repair strategy is used to improve topic coverage. Finally, large language models are employed to generate interpretable sentence-level topic labels and descriptions. Experiments demonstrate that TMCAS achieves superior clustering and interpretability while substantially reducing inference cost compared with document-wise LLM baselines.
The expansion of scientific production and the fragmentation of tools used in Systematic Literature Reviews hinder the organization, traceability, and integration of methodological stages. This study aimed to develop and functionally validate the Intelligent System for Systematic Literature Reviews (SIRSL), based on Generative Artificial Intelligence. This applied technological research adopted a descriptive approach and was conducted through iterative stages involving requirements assessment, system modeling, implementation, testing, and refinement. The system was developed using React, TypeScript, Node.js, and Firebase, integrating the Gemini model. Functional validation was carried out by applying SIRSL to a systematic review associated with a doctoral research project within the PPGADT. The initial corpus comprised 470 records, of which 58 were excluded after duplicate identification and application of the selection criteria, leaving 412 documents. The results demonstrated that SIRSL integrated functionalities for developing search strategies, importing files, detecting duplicates, screening studies, extracting data, producing indicators, and generating reports. Artificial Intelligence was employed as an assistive resource, while methodological decisions remained under the researchers’ responsibility. It is concluded that SIRSL is functionally viable and has the potential to make systematic reviews more integrated, organized, and traceable. However, further validation across different research fields and documentary datasets is still required.
A. Santos· Revista de Estudos Interdisc...· 0 citations