Table 4 Quantitative results of ablation study.
From: Knowledge graph construction for intelligent cockpits based on large language models
Methods | Evaluation metrics | ||||||
|---|---|---|---|---|---|---|---|
P | R | F1 | BLEU-4 | ROUGE-1 | ROUGE-2 | ROUGE-L | |
w/o Textual Data Preprocessing | 35.82 | 28.17 | 31.54 | 32.85 | 45.62 | 30.25 | 25.18 |
w/o Text Instruction | 54.96 | 51.63 | 53.24 | 57.82 | 68.94 | 56.81 | 48.36 |
GLM-TripleGen | 95.86 | 93.67 | 94.75 | 93.56 | 96.73 | 93.74 | 93.20 |
