ChatSOS: Vector Database Augmented Generative Question Answering Assistant in Safety Engineering

TL;DR

This paper introduces ChatSOS, a system that enhances generative question answering in safety engineering by integrating a vector database of accident reports with large language models, improving reliability and accuracy.

Contribution

It develops a specialized vector database from accident reports and demonstrates how augmenting LLMs with this database improves safety-related question answering.

Findings

Enhanced response reliability and accuracy

Superior information retrieval compared to relational databases

Potential for broader safety engineering applications

Abstract

With the rapid advancement of natural language processing technologies, generative artificial intelligence techniques, represented by large language models (LLMs), are gaining increasing prominence and demonstrating significant potential for applications in safety engineering. However, fundamental LLMs face constraints such as limited training data coverage and unreliable responses. This study develops a vector database from 117 explosion accident reports in China spanning 2013 to 2023, employing techniques such as corpus segmenting and vector embedding. By utilizing the vector database, which outperforms the relational database in information retrieval quality, we provide LLMs with richer, more relevant knowledge. Comparative analysis of LLMs demonstrates that ChatSOS significantly enhances reliability, accuracy, and comprehensiveness, improves adaptability and clarification of responses. These results illustrate the effectiveness of supplementing LLMs with an external database, highlighting their potential to handle professional queries in safety engineering and laying a foundation for broader applications.