Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models
Declarative logic programs offer a powerful and interpretable abstraction for encoding relational structure and neurosymbolic reasoning, by expressing dependencies as weighted compositional rules. However, inducing them from data remains fundamentally hard, bottlenecked by the combinatorial explosion of symbolic search...
Saurabh Mathur, Sahil Sidheekh, Bhavan Kumar Vasu et al.
· 0 citations