Requirement Discovery Using Embedded Knowledge Graph with ChatGPT
Braxton Vangundy, Nipa Phojanamongkolkij (NASA Langley Research Center) Barclay Brown (Collins Aerospace) Ramana Polavarapu, Joshua Bonner (NASA Langley Research Center)
Keywords
Large Language Models;OpenAI;ChatGPT;Urban Airspace Mobility;Requirements;Advance Air Mobility;Digital Assistant;Machine Learning;Artificial Intelligence;Graph Database;Link Prediction
Abstract
This study explores two distinct approaches to leverage LLMs in the context of Urban Airspace Mobility Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems. For the second approach, the LLM acts as an intermediary between the user and a graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user.