---
title: "A Foundation Model for Zero-Shot Logical Rule Induction"
authors:
  - "Yin Jun Phua"
doi: "10.24963/ijcai.2026/445"
url: "https://ijcai.org/proceedings/2026/445"
pdf: "https://ijcai.org/proceedings/2026/0445.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "3999-4007"
track: "Main Track"
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"
---

# A Foundation Model for Zero-Shot Logical Rule Induction

Yin Jun Phua

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 3999-4007. DOI: [10.24963/ijcai.2026/445](https://doi.org/10.24963/ijcai.2026/445)

## 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.