IEEE

IC-BERT: An Instruction Classifier Model Alleviates the Hallucination of Large Language Models in Traditional Chinese Medicine

Abstract: Large language models (LLMs) may occasionally provide inaccurate answers to questions and answers in specialized domains. Therefore, we implemented a text filter based on Bidirectional ...
IEEE

Secure Quantization of Large Language Models Based on Gaussian Naive Bayes Classifier

Abstract: This paper proposes a quantitative evaluation framework based on the Gaussian Naive Classifier, which is proposed for the quantitative evaluation of the security of Large Language Model (LLM ...