Application of Large Language Models for Generating Recommendations during Natural Hazards

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.