Table 5 Experimental results on using a random set of concepts for in-context learning
From: An evaluation of GPT models for phenotype concept recognition
| Â | Document-level | Mention-level | ||||
|---|---|---|---|---|---|---|
Precision | Recall | F1 | Precision | Recall | F1 | |
HPO-GS | 0.63 | 0.29 | 0.4 | 0.6 | 0.19 | 0.29 |
BIOC-GS | 0.55 | 0.42 | 0.48 | 0.5 | 0.37 | 0.43 |