A Foundation Model for Zero-Shot Logical Rule Induction
This work addresses the limitation of transductive ILP methods by enabling zero-shot rule induction, which is significant for scalable and reusable symbolic reasoning in AI.
NRI is a pretrained model for zero-shot logical rule induction that uses domain-agnostic statistical properties of literals, enabling generalization to new predicates without retraining. It achieves strong performance on rule recovery, robustness to noise, and zero-shot transfer to real-world benchmarks.
Inductive Logic Programming (ILP) learns interpretable logical rules from data. Existing methods are transductive: their learned parameters are bound to specific predicates and require retraining for each new task. We introduce Neural Rule Inducer (NRI), a pretrained model for zero-shot rule induction. Rather than encoding literal identities, NRI represents literals using domain-agnostic statistical properties such as class-conditional rates, entropy, and co-occurrence, which generalize across variable identities and counts without retraining. The model consists of a statistical encoder and a parallel slot-based decoder. Parallel decoding preserves the permutation invariance of logical disjunction; an autoregressive decoder would instead impose an arbitrary clause order. Product T-norm relaxation makes rule execution differentiable, allowing end-to-end training on prediction accuracy alone. We evaluate NRI on rule recovery, robustness to label noise and spurious correlations, and zero-shot transfer to real-world benchmarks, and we believe this work opens up the possibility of foundation models for symbolic reasoning. Code and the reference checkpoint are available at https://github.com/phuayj/neural-rule-inducer.