Comparative analysis of generative LLMs for labeling entities in clinical notes

Genomics & Informatics

Table 6 Micro-average precision, recall, and F1-score for entities identified by the fine-tuned encoder-based transformer models

Transformer LM	P	R	F1
BERT	0.511	0.583	0.545
RoBERTa	0.532	0.616	0.570
XLM-RoBERTa	0.512	0.585	0.546
BIO-BERT	0.541	0.622	0.579
BIO-Clinical-BERT	0.519	0.600	0.557
BIOMED-RoBERTa	0.527	0.617	0.569
Clinical-XLM-RoBERTa	0.547	0.597	0.571

ISSN: 2234-0742