Research on false propaganda detection technology based on LLM and BERT
Lidong Xing, Nannan Hou, Zhiqing Zhang, Ke Li, Fangxu Meng · 2025
False propaganda, as one of the unfair competition behaviors, seriously damages consumer rights and disrupts market order. This article aims to design a false propaganda detection technology based on LLM and BERT for dishonest behavior caused by false propaganda. By annotating false propaganda text data with LLM and training a false propaganda detection model based on BERT, the rapid development of the false propaganda detection model and effective cost savings in manual annotation have been achieved. The results show that this method has good performance and efficiency, and can meet practical engineering needs. It has certain application and reference value for model development in market supervision fields such as false propaganda.