Relational Triplet Extraction on NYC-Large (test)
46GPT AccuracyUrbanKGent-13B
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| UrbanKGent-13BModel Scale=13B2024.02 | 46 | 4.56 | 55 | |
| UrbanKGent-7BModel Scale=7B2024.02 | 44 | 4.27 | 53 | |
| UrbanKGent InferenceMode=Inference setting2024.02 | 43 | 4.13 | 51 | |
| UrbanKGent-8BModel Scale=8B2024.02 | 43 | 4.07 | 52 | |
| ICLLearning Paradigm=In-context-learning2024.02 | 39 | 4.36 | 48 | |
| VFTLearning Paradigm=Vanilla Fine-tuning2024.02 | 37 | 4.05 | 45 | |
| ZSLLearning Paradigm=Zero-shot-learning2024.02 | 36 | 4.01 | 42 |