Two-stage few-sample automatic fact checking method, electronic equipment and storage medium

Through the two-stage automatic fact verification method of few samples, the BM25 and Seq2Seq language models are used for document retrieval and sentence selection, and the pre-trained language model is fine-tuned for declaration verification, which solves the problem of insufficient information verification efficiency and accuracy in the existing technology, and realizes efficient and low-cost information verification.

CN119691152AActive Publication Date: 2025-03-25HARBIN INST OF TECH
2 Cites 2 Cited by

Patent Information

Application Number
CN202411828667.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-12
Publication Date
2025-03-25
Estimated Expiration
2044-12-12

AI Technical Summary

Technical Problem

In the era of information explosion, it has become difficult to quickly and accurately discover false information. The existing manual fact verification is time-consuming and resource-intensive, making it difficult to keep up with information flow in real time.

Method used

A two-stage automatic fact verification method for few samples is proposed, document retrieval is performed through the BM25 model construction index, and sentence selection is performed in combination with the Seq2Seq language model and fine-tuning of the pre-trained language model for declaration verification.

Benefits of technology

It realizes that without requiring a large amount of training data, improves the accuracy and efficiency of information verification, reduces the cost and workload of data collection and processing, and has a small amount of model parameters and low computing resource requirements.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a two-stage few-sample automatic fact checking method, electronic equipment and a storage medium, and belongs to the technical field of information processing. In order to improve the accuracy and efficiency of information verification, the method comprises the following steps: selecting a public fact verification data set to construct a test set; constructing an evidence retrieval model, and retrieving the documents of the test set by adopting the evidence retrieval model to obtain candidate documents; constructing a sentence selection model, inputting each sentence in the candidate document and the statement into a prompt template to be combined into the input of the sentence selection model, and outputting the correlation score of the sentences as an evidence sentence for statement verification; constructing a pre-training language model and finely adjusting the pre-training language model; and inputting an evidence sentence for statement verification and a statement to be verified into a prompt template to be combined into input of a pre-training language model, inputting the input into the pre-training language model after fine tuning to obtain natural language output, then mapping the natural language output to a classification label, and calculating a prediction score according to the generation probability of an output sequence to obtain a final prediction result.
Need to check novelty before this filing date? Find Prior Art