Exploring the Potential of Large-Scale Language Models in Interacting with Academic and Scientific Curricular Data

Resumo

The increasing availability of academic and scientific curriculum data represents a valuable opportunity for advancing interdisciplinary research, assessing competencies, and building collaborative networks. However, the complexity, heterogeneity, and volume of these data pose significant challenges to their analysis and interpretation. This paper proposes the use of Large Language Models (LLMs) as a central tool to enable intelligent and scalable interaction with academic curriculum data. We discuss approaches for ingesting, contextualizing, and extracting knowledge from large volumes of curriculum data, highlighting the potential of LLMs to generate automatic summaries of academic trajectories, identify areas of expertise, suggest collaborations, and support institutional evaluation processes. The proposal aims to explore the full potential of these technologies to transform the way we interact with academic data and boost institutional intelligence in scientific and educational environments.