HORAE: A Domain-Agnostic Language for Automated Service Regulation

TL;DR

This paper introduces Horae, a domain-agnostic language for modeling regulation rules, and demonstrates how a fine-tuned large language model, RuleGPT, automates regulation across diverse domains, outperforming GPT-3.5 and matching GPT-4.

Contribution

The paper presents Horae, a unified regulation language, and a fine-tuned RuleGPT model that automates regulation modeling across multiple domains, enhancing generalization and automation.

Findings

RuleGPT outperforms GPT-3.5 in regulation tasks.

RuleGPT performs on par with GPT-4.

Framework is effective across various real-world domains.

Abstract

Artificial intelligence is rapidly encroaching on the field of service regulation. However, existing AI-based regulation techniques are often tailored to specific application domains and thus are difficult to generalize in an automated manner. This paper presents Horae, a unified specification language for modeling (multimodal) regulation rules across a diverse set of domains. We showcase how Horae facilitates an intelligent service regulation pipeline by further exploiting a fine-tuned large language model named RuleGPT that automates the Horae modeling process, thereby yielding an end-to-end framework for fully automated intelligent service regulation. The feasibility and effectiveness of our framework are demonstrated over a benchmark of various real-world regulation domains. In particular, we show that our open-sourced, fine-tuned RuleGPT with 7B parameters suffices to outperform GPT-3.5 and perform on par with GPT-4o.