Table 5 Ratio of documents with correctly parsed entities
From: Comparative analysis of generative LLMs for labeling entities in clinical notes
Model | Variation 2 | Variation 3 |
|---|---|---|
llama-2-7b | 0.16 | 0.16 |
llama-2-7b-chat | 0.59 | 0.34 |
codellama-7b-instruct | 0.99 | 0.16 |
mistral-7b-v0.1 | 0.13 | 0.11 |
mistral-7b-instruct-v0.2 | 0.98 | 0.99 |
mixtral-8x7b-instruct-v0.1 | 0.86 | 0.98 |