Saved in:
Bibliographic Details
Main Authors: Yang, Yang, Wu, Jiemin, Yue, Yutao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.21486
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908773706104832
author Yang, Yang
Wu, Jiemin
Yue, Yutao
author_facet Yang, Yang
Wu, Jiemin
Yue, Yutao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21486
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hypothesis Generation via LLM-Automated Language Bias for ILP
Yang, Yang
Wu, Jiemin
Yue, Yutao
Artificial Intelligence
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.
title Hypothesis Generation via LLM-Automated Language Bias for ILP
topic Artificial Intelligence
url https://arxiv.org/abs/2505.21486