Declarative Integration and Management of Large Language Models through Finite Automata: Application to Automation, Communication, and Ethics

TL;DR

This paper presents a novel, declarative architecture using finite automata to efficiently integrate and manage multiple Large Language Models for diverse applications like automation, communication, and ethics.

Contribution

It introduces a general, declarative framework that simplifies the complex integration of LLMs with minimal programming, leveraging finite automata and event management.

Findings

Effective integration of LLMs demonstrated in automation tasks

Flexible management of LLMs for communication and ethics applications

Reduced programming effort for complex LLM workflows

Abstract

This article introduces an innovative architecture designed to declaratively combine Large Language Models (LLMs) with shared histories, and triggers to identify the most appropriate LLM for a given task. Our approach is general and declarative, relying on the construction of finite automata coupled with an event management system. The developed tool is crafted to facilitate the efficient and complex integration of LLMs with minimal programming effort, especially, but not only, for integrating methods of positive psychology to AI. The flexibility of our technique is demonstrated through applied examples in automation, communication, and ethics.