Building Trust in Conversational AI: A Comprehensive Review and Solution Architecture for Explainable, Privacy-Aware Systems using LLMs and Knowledge Graph

TL;DR

This paper introduces a comprehensive review tool for LLMs and proposes an architecture combining Knowledge Graphs with LLMs to enhance trustworthiness, factual accuracy, and privacy in conversational AI systems.

Contribution

It presents LLMXplorer, a detailed review tool for LLMs, and a novel architecture integrating Knowledge Graphs with LLMs for improved transparency and security in conversational AI.

Findings

Validated architecture with real-world AI news data

Enhanced factual accuracy and data security in conversational AI

Provided insights into ethical and regulatory implications

Abstract

Conversational AI systems have emerged as key enablers of human-like interactions across diverse sectors. Nevertheless, the balance between linguistic nuance and factual accuracy has proven elusive. In this paper, we first introduce LLMXplorer, a comprehensive tool that provides an in-depth review of over 150 Large Language Models (LLMs), elucidating their myriad implications ranging from social and ethical to regulatory, as well as their applicability across industries. Building on this foundation, we propose a novel functional architecture that seamlessly integrates the structured dynamics of Knowledge Graphs with the linguistic capabilities of LLMs. Validated using real-world AI news data, our architecture adeptly blends linguistic sophistication with factual rigour and further strengthens data security through Role-Based Access Control. This research provides insights into the evolving landscape of conversational AI, emphasizing the imperative for systems that are efficient, transparent, and trustworthy.