HORAE: A Domain-Agnostic Language for Automated Service Regulation
This work addresses the challenge of generalizing automated service regulation across domains, offering a domain-agnostic solution that could benefit regulators and service providers, though it appears incremental as it builds on existing language model techniques.
The paper tackles the problem of domain-specific AI-based service regulation by introducing Horae, a unified specification language for modeling multimodal regulation rules across diverse domains, and demonstrates that their fine-tuned RuleGPT with 7B parameters outperforms GPT-3.5 and performs on par with GPT-4o on real-world benchmarks.
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.