Evaluating the Performance of RAG Methods for Conversational AI in the Airport Domain

TL;DR

This paper evaluates three Retrieval-Augmented Generation methods for conversational AI in airports, highlighting Graph RAG's superior accuracy and safety features for dynamic, reasoning-involving queries.

Contribution

It introduces and compares three RAG-based approaches for airport-specific conversational AI, emphasizing Graph RAG's effectiveness and safety improvements.

Findings

Graph RAG achieved 91.49% accuracy with fewer hallucinations.

Traditional RAG had 84.84% accuracy but risked hallucinations.

SQL RAG and Graph RAG are recommended for airport environments.

Abstract

Airports from the top 20 in terms of annual passengers are highly dynamic environments with thousands of flights daily, and they aim to increase the degree of automation. To contribute to this, we implemented a Conversational AI system that enables staff in an airport to communicate with flight information systems. This system not only answers standard airport queries but also resolves airport terminology, jargon, abbreviations, and dynamic questions involving reasoning. In this paper, we built three different Retrieval-Augmented Generation (RAG) methods, including traditional RAG, SQL RAG, and Knowledge Graph-based RAG (Graph RAG). Experiments showed that traditional RAG achieved 84.84% accuracy using BM25 + GPT-4 but occasionally produced hallucinations, which is risky to airport safety. In contrast, SQL RAG and Graph RAG achieved 80.85% and 91.49% accuracy respectively, with significantly fewer hallucinations. Moreover, Graph RAG was especially effective for questions that involved reasoning. Based on our observations, we thus recommend SQL RAG and Graph RAG are better for airport environments, due to fewer hallucinations and the ability to handle dynamic questions.