Table 5 Calculated metrics.

From: Automated generation of discharge summaries: leveraging large language models with clinical data

Type of score

Score+

ROUGE-1

0.25 ± 0.04

ROUGE-2

0.06 ± 0.03

ROUGE-L

0.24 ± 0.04

BERTScore*

0.64 ± 0.01

  1. +Mean ± Standard deviation.
  2. *Computed with “facebook/bart-large-mnli”.
Back to article page