Year: 2024
Type: article
Abstract: With the rapid development of large language models, their application in various industries is becoming more and more common, especially in the power sector. Electricity power standard knowledge, as an industry specification for electric power equipment, engineering construction and operation management, can guide product production and engineering practice to improve production efficiency and quality level. In order to help solve the problem of low efficiency of electric power standard knowledge supply and assist the generation of electric power standard knowledge, we proposes an electric standard knowledge auxiliary generation method based on retrieval enhancement generation, which uses the retrieval model and evaluation model to provide large language model with accurate external knowledge, and then uses the generation model to provide a more efficient and accurate solution for the generation of standard knowledge in the electric industry. The experimental results indicate that the approach introduced in this paper can effectively generate accurate electricity-related knowledge and holds significant practical value.
DOI: 10.52152/4073
Authors: Xiaoxuan Fan, Sai Zhang, Xiao Liang, Zhihao Wang, Tao Peng
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4405917210