Large Language Models (LLMs) have revolutionized natural language processing, demonstrating remarkable capabilities in text generation, comprehension, and reasoning. However, their reliance on implicit statistical patterns often limits factual accuracy, reasoning depth, and consistency. Integrating external knowledge sources presents a promising approach to overcoming these challenges, enhancing model reliability and interpretability. The candidate will explore the application of novel techniques for both knowledge base construction and reasoning strategies to enhance LLM performance. The research will focus on designing methods to structure, integrate, and dynamically update knowledge sources while developing advanced reasoning mechanisms to exploit these sources’ interconnections effectively.

This PhD opportunity is a collaboration between Fondazione Bruno Kessler and the University of Roma Sapienza – NATIONAL PHD IN ARTIFICIAL INTELLIGENCE. For more information on this call and how to apply, please visit the website of the University of Roma Sapienza (https://www.uniroma1.it/it/pagina/ammissione-ai-corsi-di-dottorato).