Predicate Renaming via Large Language Models
This addresses a readability and interpretability issue in Inductive Logic Programming, but it is incremental as it applies existing LLM capabilities to a specific domain problem.
The paper tackled the problem of naming unnamed predicates in logic rules, which hinders readability and reusability, by using Large Language Models to provide semantically meaningful suggestions, with evaluation on hand-crafted rules indicating potential for this task.
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.