ChatSOS: Vector Database Augmented Generative Question Answering Assistant in Safety Engineering
This addresses the need for more reliable AI assistance in safety engineering, though it is incremental as it applies an existing method (vector database augmentation) to a new domain.
The study tackled the problem of unreliable responses from large language models (LLMs) in safety engineering by augmenting them with a vector database built from 117 explosion accident reports, resulting in significant enhancements in reliability, accuracy, and comprehensiveness of the models.
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.