Skip to main content
. 2025 Aug 24;8:541. doi: 10.1038/s41746-025-01940-4

Table 2.

Data extraction agent performance as a binary classifier

Precision (Positive) Recall (Positive) F-1(Positive) Overall accuracy
Fine-tuned LLaMa 3.1 8B instruct 0.74 (0.72, 0.76) 0.89 (0.88, 0.91) 0.81 (0.79, 0.83) 0.93 (0.91, 0.95)
Ensemble (Li et al. 2023) 0.71 (0.69, 0.73) 0.84 (0.82, 0.86) 0.77 (0.75, 0.79) 0.91 (0.89, 0.93)