Table 3 Evaluation results of different models in NER task.

From: Research on the proximity relationships of psychosomatic disease knowledge graph modules extracted by large language models

Model

Precision

Recall

F1

BERT

0.91

0.63

0.74

LLM

0.86

0.71

0.78

LLaMA fine-tuned by LoRA

0.93

0.76

0.83

Back to article page