# Hypothesis Generation via LLM-Automated Language Bias for ILP

arXiv: https://arxiv.org/abs/2505.21486 · HTML: https://mlsanity.com/paper/2505.21486/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 12 of 12)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Learning Explanatory Rules from Noisy Data](https://mlsanity.com/paper/1711.04574/) (2017)
- [LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers](https://mlsanity.com/paper/2310.15164/) (2023)
- [Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model](https://mlsanity.com/paper/1511.01644/) (2015)
- [Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement](https://mlsanity.com/paper/2310.08559/) (2023)
- [Inductive logic programming at 30: a new introduction](https://mlsanity.com/paper/2008.07912/) (2020)
- [Learning programs by learning from failures](https://mlsanity.com/paper/2005.02259/) (2020)
- [MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses](https://mlsanity.com/paper/2410.07076/) (2024)
- [Large Language Models can Learn Rules](https://mlsanity.com/paper/2310.07064/) (2023)
- [Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks](https://mlsanity.com/paper/2112.03324/) (2021)
- [LLM-ARC: Enhancing LLMs with an Automated Reasoning Critic](https://mlsanity.com/paper/2406.17663/) (2024)
- [Learning MDL logic programs from noisy data](https://mlsanity.com/paper/2308.09393/) (2023)

## Built on by (most cited first, 2 of 2)

- [Interestingness First Classifiers](https://mlsanity.com/paper/2508.19780/) (2025)
- [ADVENT: LLM-Driven Automatic Predicate Invention for ILP](https://mlsanity.com/paper/2607.01585/) (2026)

## Abstract (arXiv)

Inductive Logic Programming (ILP) is a principled approach for generalizing regularities from data and constructing hypotheses as interpretable logic programs. However, a key limitation is its reliance on expert-crafted language bias - the predicate inventory, types, and mode declarations that delimit the search space. We propose hypothesis generation via LLM-automated language bias: multi-agent LLMs design the bias from raw text and translate descriptions into typed facts, and a robust ILP solver induces rules under a global consistency objective. This approach reduces traditional ILP's reliance on predefined symbolic structures and the noise sensitivity of LLM-only pipelines that directly generate hypotheses as text or code. Extensive experiments in diverse, challenging scenarios validate superior performance, providing a practical, explainable, and verifiable route to hypothesis generation.