Research on Performance Optimization of BERT Model in AI-Generated Text Detection

With the rapid development of large language models, the text generated by artificial intelligence (AI) is increasingly approaching the human level in terms of fluency, coherence and factuality. It brings unprecedented challenges to many fields such as information security and academic integrity. Therefore, the research on AI-generated text detection technology has become crucial. In recent years, detection methods based on pre-trained language models have shown significant advantages and become a research hotspot in this field. This paper reviews the representative research progress on the performance optimization of Bidirectional Encoder Representations from Transformers (BERT) model in the field of AI-generated text detection in recent years. It also discusses the limitations of the current BERT detection model, and looks forward to future research directions. Research analysis shows that the detection performance and robustness of BERT model in cross-domain and AI generation model can be significantly improved by using optimization strategies such as feature fusion and adversarial training. These results provide a valuable reference for the further development of AI-generated text detection technology.