Dataset | BERT-Large | BART-Large | Flan-T5-Large | Flan-T5-XL | GPT-3 | BLOOM-1b7 | BLOOM-3b | Flan-T5-Large* |
Flan-T5-XL* |
GPT-4 | GPT-3.5$ | LLaMA-7B | PubMedBERT |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
UMLS | 40.10 | 42.35 | 46.02 | 49.52 | 38.84 | 43.12 | 42.70 | 49.05 | 53.05 | 41.31 | 37.51 | 20.34 | 42.68 |
Flan-T5-Large*
and Flan-T5-XL*
are Few-shot learning results for datasets.