Abductive Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models
This addresses the problem of automating logical reasoning from limited data for researchers and practitioners in AI, though it is incremental by combining existing methods.
The paper tackles the challenge of abductive logical rule induction from unstructured inputs by proposing ILP-CoT, which bridges Inductive Logic Programming and Multimodal Large Language Models to improve accuracy and efficiency, achieving strong performance on benchmarks and enabling applications like text-to-image generation.
We propose ILP-CoT, a method that bridges Inductive Logic Programming (ILP) and Multimodal Large Language Models (MLLMs) for abductive logical rule induction. The task involves both discovering logical facts and inducing logical rules from a small number of unstructured textual or visual inputs, which still remain challenging when solely relying on ILP, due to the requirement of specified background knowledge and high computational cost, or MLLMs, due to the appearance of perceptual hallucinations. Based on the key observation that MLLMs could propose structure-correct rules even under hallucinations, our approach automatically builds ILP tasks with pruned search spaces based on the rule structure proposals from MLLMs, and utilizes ILP system to output rules built upon rectified logical facts and formal inductive reasoning. Its effectiveness is verified through challenging logical induction benchmarks, as well as a potential application of our approach, namely text-to-image customized generation with rule induction. Our code and data are released at https://github.com/future-item/ILP-CoT.