Inductive Logic Programming

Also known as ILP

Inductive Logic Programming (ILP) studies how to infer logical rules or programs from examples and background knowledge, making it useful when systems need explanations as well as predictions. Approaches include symbolic search over clauses, answer-set-programming learners such as ILASP and Popper, differentiable rule-learning networks, and language models that propose hypotheses for formal verification. ILP is used for relational prediction, program synthesis, visual concept learning, and rule-based control, including safety checks for agents. A central challenge is scaling search and inventing useful predicates while keeping rules interpretable and able to generalize beyond the examples used for learning.

Latest papers

21 papers3 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models
Oct 8, 2026Saurabh Mathur, Sahil Sidheekh, Bhavan Vasu +4Probabilistic Logic Inductive Logic Programming
Technische Universität Darmstadt · The University of Texas at Dallas · AT&T CDO +1
Teaching a Minimalist Machine to Discover Recursive Programs for Arithmetic
Oct 5, 2026Dominik Magiera, Christiane Wiebel-Herboth, Frank JäkelCognitive Modeling Program Synthesis
Centre for Cognitive Science & Institute of Psychology, Technische Universität Darmstadt, Germany · Honda Research Institute Europe GmbH, Offenbach am Main, Germany
WAMpy: Efficient Synthesis of Prolog Programs in Python
Oct 2, 2026Dominik Magiera, Lukas Röhrig, Frank JäkelProgram Synthesis Logic Programming
Centre for Cognitive Science & Institute of Psychology, Technische Universität Darmstadt, Germany
QILP-0: Constructing Observational Declarative Twins of Quantum Circuits
Sep 1, 2026Marina de la Cruz Echeandía, César Luis Alonso, Tony Ribeiro +1Inductive Logic Programming
Universidad Internacional de la Rioja UNIR, Escuela Superior de Ingeniería y Tecnología, Logroño, Spain · Universidad de Oviedo, Departamento de Informática, Gijón, 33204, Spain · Nantes Université, École Centrale Nantes, CNRS, LS2N, UMR 6004, 44000, Nantes, France +1
Hypothesis Frontier: Verifier Guided LLM and Symbolic Search for First-Order Induction
Aug 11, 2026Serafim BatzoglouSymbolic Reasoning LLM-Based Program Synthesis
Independent Researcher
Hypercubes, Hyperplanes, and Constraint-Induced Complexity Collapse in Atomic Concept Learning
Aug 3, 2026Irene TsaparaInductive Logic Programming
National University, San Diego, United States
Pretrain on Small Synthetic Data, Scale Large for Free: Symmetry-Aware Foundation Model for Logic Rule Induction
Aug 1, 2026Yin Jun PhuaInterpretable ML Equivariant Neural Networks
Institute of Science Tokyo
An Unofficial FastLAS Tutorial: A Programmer's Guide
Jul 26, 2026Fabio Aurelio D'AsaroLogic Programming Inductive Logic Programming
University of Verona, Italy · University College London, United Kingdom
Reason Popper-ly: Patching In-Context Reasoning with Inductive Logic Programming
Jul 25, 2026Zirong Chen, Meiyi MaReasoning Trace Analysis Reasoning Consistency in Language Models
Department of Computer Science, Vanderbilt University, USA
ADVENT: LLM-Driven Automatic Predicate Invention for ILP
Jul 2, 2026Tingting Yu, Pei-Cing Huang, Chan Hsu +2Logic Programming Inductive Logic Programming
Department of Information Management National Sun Yat-Sen University Kaohsiung, Taiwan
AutoSpec: Safety Rule Evolution for LLM Agents via Inductive Logic Programming
Jun 23, 2026Pingchuan Ma, Zhaoyu Wang, Zimo Ji +5LLM Guardrails Program Synthesis
Zhejiang University of Technology · HKUST
Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming
May 26, 2026Oleh Borys, Karla StepanovaRobot Skill Learning Robotic Manipulation
Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague.
From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
May 20, 2026Nura Aljaafari, Danilo S. Carvalho, Andre FreitasCircuit Discovery Mechanistic Interpretability
Department of Computer Science, University of Manchester, United Kingdom · CRUK National Biomarker Centre, University of Manchester, United Kingdom · Idiap Research Institute, Switzerland
A Foundation Model for Zero-Shot Logical Rule Induction
May 6, 2026Yin Jun PhuaZero-Shot Learning Neuro-Symbolic Reasoning
Institute of Science Tokyo
ANDRE: An Attention-based Neuro-symbolic Differentiable Rule Extractor for Inductive Logic Programming
May 5, 2026Iman Sharifi, Peng Wei, Saber FallahLogic Programming Differentiable Programming
Dept. of Mechanical and Aerospace Engineering, George Washington University, USA · Dept. of Mechanical Engineering Sciences, University of Surrey, UK
AGEL-Comp: A Neuro-Symbolic Framework for Compositional Generalization in Interactive Agents
Apr 29, 2026Mahnoor Shahid, Hannes RotheNeuro-Symbolic AI Inductive Logic Programming
Universität Duisburg-Essen, Essen, Germany
Visual Perceptual to Conceptual First-Order Rule Learning Networks
Apr 9, 2026Kun Gao, Davide Soldà, Thomas Eiter +1Differentiable Logic Inductive Logic Programming
Zhongguancun Academy, Beijing, China · Vienna University of Technology (TU Wien), Vienna, Austria · National Institute of Informatics, Tokyo, Japan
Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach
Apr 8, 2026Daniele Fossemò, Filippo Mignosi, Giuseppe Placidi +3Neural Network Interpretability Preference Learning
Department of Information Engineering, Computer Science and Mathematics, University of L’Aquila, Italy · ICAR-CNR, Palermo, Italy · Department of Life, Health and Environmental Sciences, University of L’Aquila, Italy +2
INDUCTION: Finite-Structure Concept Synthesis in First-Order Logic
Feb 21, 2026Serafim BatzoglouSymbolic Reasoning Inductive Inference
Independent Researcher.
Ultra Strong Machine Learning: LLM-Generated Explanations Do Not Yet Suffice for Teaching Humans Active Learning Strategy
Aug 31, 2025Lun Ai, Johannes Langer, Ute Schmid +1Active Learning Human-in-the-Loop AI
Department of Computing, Imperial College London, UK · Faculty Information Systems and Applied Computer Science, University of Bamberg, Germany
Neuro-symbolic Weak Supervision: Theory and Semantics
Mar 24, 2025Nijesh Upreti, Vaishak BelleWeakly Supervised Learning Neuro-Symbolic Reasoning
School of Informatics, University of Edinburgh, Edinburgh, UK

Oct 8, 2026J/K move · Enter open · S save

Learning Probabilistic Logic Programs with Functional Gradient Guided Language Models

Saurabh Mathur, Sahil Sidheekh, Bhavan Vasu, Farbod Tavakkoli+3

Technische Universität Darmstadt · The University of Texas at Dallas · AT&T CDO+1

Probabilistic Logic Inductive Logic Programming LLM-Based Program Synthesis Ensemble Learning

Open paper AskPDF arXiv

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 which the weak learner is a first-order rule and the intractable inner search is delegated to an LLM proposal oracle. We evaluate grasp on four relational benchmarks spanning molecular toxicity prediction (Tox21), mutagenesis, and citation matching (Cora), and show that it improves over purely symbolic, neural, and LLM-based baselines, while producing interpretable weighted rule ensembles. By replacing combinatorial search with gradient-guided LLM hypothesis generation, grasp retains boosting guarantees without sacrificing the transparency of symbolic outputs.