Ciao, I’m Leonardo! I’m a PhD student in Information Engineering and Computer Science at University of Trento, supervised by Prof. Raffaella Bernardi.
My research focuses on the reasoning capabilities of Large Language Models (LLMs) at the intersection of AI and cognitive science.
I’m passionate about exploring topics such as:
-
LLM Reasoning Processes: How do LLMs perform reasoning tasks? What computational mechanisms underlie their reasoning processes, and how do these mechanisms compare to formal logic systems or human-like reasoning?
-
Behavioral Analysis of LLMs: Inspired by cognitive psychology, can we use systematic behavioral experiments to analyze and interpret the decision-making processes of LLMs? What insights can this provide into their strengths and limitations?
-
Comparative Analysis of Biases: What biases emerge in LLMs, and how do they compare to human cognitive biases? Are there biases unique to LLMs that arise from their architecture or training data?
If you have any questions about my research or if you’re interested in collaborating, feel free to reach out!
Interests
- Language Models
- Reasoning
- Natural Language Processing
- Cognitive Science
- Machine Learning