Robust Hypothesis Generation: LLM-Automated Language Bias for Inductive Logic Programming
This addresses the need for automated, explainable hypothesis generation in AI cognition, representing a novel method rather than an incremental improvement.
The paper tackles the problem of automating robust hypothesis generation in open environments by integrating a multi-agent LLM system with Inductive Logic Programming to autonomously define symbolic vocabulary from raw text, overcoming traditional bottlenecks. It reports superior performance in diverse scenarios, though no concrete numbers are provided.
Automating robust hypothesis generation in open environments is pivotal for AI cognition. We introduce a novel framework integrating a multi-agent system, powered by Large Language Models (LLMs), with Inductive Logic Programming (ILP). Our system's LLM agents autonomously define a structured symbolic vocabulary (predicates) and relational templates , i.e., \emph{language bias} directly from raw textual data. This automated symbolic grounding (the construction of the language bias), traditionally an expert-driven bottleneck for ILP, then guides the transformation of text into facts for an ILP solver, which inductively learns interpretable rules. This approach overcomes traditional ILP's reliance on predefined symbolic structures and the noise-sensitivity of pure LLM methods. Extensive experiments in diverse, challenging scenarios validate superior performance, paving a new path for automated, explainable, and verifiable hypothesis generation.