Table 3 Ablation experiment results of different prompt designs.

From: Fine-tuned large language models with structured prompts enable efficient construction of lung cancer knowledge graphs

Variant name

Precision

Recall

F1 score

Full template

0.83

0.80

0.82

w/o system role

0.77

0.73

0.75

w/o triple schema

0.71

0.65

0.68

w/o COT reasoning

0.75

0.72

0.73

Free generation

0.64

0.58

0.61

Back to article page