Structured Reasoning and Automated Planning in AI Language Models
Scientific-Disciplinary Group
09/IINF-05 - Information Processing Systems
Description
The research program aims to study and develop innovative methods and systems for automated reasoning and planning through artificial intelligence language models and neuro-symbolic techniques. An important aspect of the research concerns model interpretability, investigating whether and to what extent language models develop structured internal representations of knowledge or rely primarily on statistical regularities. Through interpretability techniques, the research aims to localize such knowledge within the models and evaluate the impact of different training or adaptation strategies on the quality, robustness, and generalizability of the learned representations.
Job posting website
Number of positions
1
Funding body
Università degli studi di Brescia
Selection process
Click to expand
View the original posting on the MUR website: Go to MUR website