Title: Data clustering methods and large language models applications Authors:  Mantas Lukauskas - Kaunas University of Technology (Lithuania) [presenting]
Abstract: The escalating complexity and volume of data in various scientific domains necessitate advanced methodologies for efficient data analysis and interpretation. The purpose is to delve into the synergy between data clustering methods and large language models (LLMs) to foster innovative approaches in handling extensive datasets. Data clustering, a pivotal aspect of data mining, involves grouping a set of objects in such a way that objects in the same group are more similar to each other than to those in other groups. It serves as a foundational step in the analysis, enabling the identification of intrinsic patterns and structures within the data. Simultaneously, the advent of LLMs, characterized by their vast parameter spaces and deep learning capabilities, has revolutionized natural language processing and understanding. It explores how these models can be leveraged to enhance the interpretability and applicability of clustering results, particularly in handling unstructured data, such as text. Through a synthesis of theoretical discussion and practical case studies, the presentation aims to highlight the potential gains of integrating clustering techniques with LLMs, offering insights into their applicability across various fields, from bioinformatics to social media analytics. This investigation not only broadens the understanding of data analysis methodologies but also opens avenues for future research in optimizing data handling and knowledge extraction processes.