Table 9 Average ( ± standard deviation) P, R, F1 and Acc of the three LLM: RL-BNE, BIO-CLI and XRB.

From: A clinical narrative corpus on nut allergy: annotation schema, guidelines and use case

Model

Precision

Recall

F-measure

Accuracy

RL-BNE

0.852( ± 0.016)

0.870( ± 0.009)

0.861( ± 0.011)

0.958( ± 0.004)

BIO-CLI

0.856( ± 0.013)

0.877( ± 0.009)

0.862( ± 0.008)

0.957( ± 0.004)

XRB

0.854( ± 0.009)

0.865( ± 0.005)

0.861( ± 0.006)

0.959( ± 0.002)