An intelligent knowledge question answering method, device, equipment and storage medium

Abstract

The application discloses an intelligent knowledge question answering method and device, equipment and a storage medium, and relates to the technical field of natural language processing. The method comprises the following steps: inputting a knowledge question answering request into a user intention recognition model to recognize the questioning behavior intention of the user; if the questioning behavior intention is an objective query type intention, corresponding factual knowledge is obtained from a knowledge base, and an initial knowledge answer is obtained by using a large language model to answer the question answering request; the hidden state vector of the last token of each sentence in the initial knowledge answer in the middle layer of the model is extracted; the hidden state vector is processed by dimensionality increasing using a sparse autoencoder; the state vector after dimensionality increasing is input into an MLP classifier to predict the illusion probability of each sentence in the initial knowledge answer, and the sentences in the initial knowledge answer are marked based on the illusion probability to obtain a target knowledge answer. The application can reduce the potential risks caused by model illusion and improve the quality and accuracy of the knowledge question answering result.

Images