לימוד תוכניות לוגיקה הסתברותיות עם מודלים שפה מונחים גרדיאנט

תקציר מקורי באנגליתarXiv:2610.12303v1 Announce Type: new Abstract: 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 spaces. LLMs have recently emerged as powerful hypothesis generators, but when used in isolation, they lack the capacity to do systematic inductive reasoning needed to reliably synthesize valid programs that fit complex relational distributions. We introduce grasp (Gradient-boosted Synthesis of Probabilistic logic programs), a neurosymbolic framework that casts relational structure learning as functional gradient boosting in wh