Predicate Renaming via Large Language Models

TL;DR

This paper explores using Large Language Models to assign meaningful names to unnamed predicates in logic rules, aiming to improve interpretability and reusability of logic theories.

Contribution

It demonstrates the potential of LLMs to generate semantically meaningful predicate names in logic rules, a novel application in Inductive Logic Programming.

Findings

LLMs can suggest meaningful predicate names

Improves readability of logic rules

Potential to enhance logic rule interpretability

Abstract

In this paper, we address the problem of giving names to predicates in logic rules using Large Language Models (LLMs). In the context of Inductive Logic Programming, various rule generation methods produce rules containing unnamed predicates, with Predicate Invention being a key example. This hinders the readability, interpretability, and reusability of the logic theory. Leveraging recent advancements in LLMs development, we explore their ability to process natural language and code to provide semantically meaningful suggestions for giving a name to unnamed predicates. The evaluation of our approach on some hand-crafted logic rules indicates that LLMs hold potential for this task.