{"type":"ScholarlyArticle","title":"A Foundation Model for Zero-Shot Logical Rule Induction","authors":[{"name":"Yin Jun Phua","slug":"yin-jun-phua","given":"Yin Jun","family":"Phua","affiliation":""}],"abstract":"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. An extended version with full appendices is available at https://arxiv.org/abs/2605.04916.","doi":"10.24963/ijcai.2026/445","url":"https://ijcai.org/proceedings/2026/445","pdf":"https://ijcai.org/proceedings/2026/0445.pdf","markdown":"https://ijcai.org/proceedings/2026/445.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/445","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Knowledge Representation and Reasoning","track":"Main Track","number":445,"pages":{"first":3999,"last":4007},"keywords":["Machine Learning: Foundation models","Machine Learning: Neuro-symbolic methods/Abductive Learning","Knowledge Representation and Reasoning: Learning and reasoning","Knowledge Representation and Reasoning: Logic programming"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}