Named Entity Recognition on DynamicNER 1.0
73.1NER Score (en)CascadeNER
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| CascadeNEREvaluation Protocol=Dynamic-Supervised, Base Model=GPT-4o2024.09 | 73.1 | 67.1 | 67.8 | 66.9 | 67.6 | 68.3 | 67.4 | 67.9 | |
| CascadeNEREvaluation Protocol=Dynamic-Supervised, Base Model=Qwen2.5-7B2024.09 | 68.2 | 61.5 | 55.3 | 52.9 | 51.4 | 64.5 | 58.8 | 55.3 | |
| CascadeNEREvaluation Protocol=Dynamic-Supervised, Base Model=Qwen2.5-1.5B2024.09 | 62.8 | 55.7 | 52.8 | 51.1 | 48.8 | 58.9 | 54.1 | 52.7 | |
| CascadeNEREvaluation Protocol=Dynamic-Fewshot, Base Model=GPT-4o2024.09 | 61.3 | 57.4 | 56.9 | 56.2 | 56 | 59.7 | 56.8 | 56.4 | |
| GPT-NEREvaluation Protocol=Dynamic-Supervised, Base Model=GPT-4o2024.09 | 60.6 | 57.3 | 56.5 | 55.6 | 55.9 | 58.4 | 54.9 | 53.8 | |
| CascadeNEREvaluation Protocol=Dynamic-Fewshot, Base Model=Qwen2.5-7B2024.09 | 55.7 | 49.9 | 49.7 | 46.5 | 46.1 | 52.9 | 50.2 | 50 | |
| PromptNEREvaluation Protocol=Dynamic-Supervised, Base Model=GPT-4o2024.09 | 53 | 50.5 | 51.2 | 47.9 | 50.2 | 52.3 | 48.7 | 48.5 | |
| GPT-NEREvaluation Protocol=Dynamic-Supervised, Base Model=Qwen2.5-7B2024.09 | 52.3 | 46.4 | 44.8 | 44.8 | 45.7 | 48.1 | 42.3 | 42.1 | |
| CascadeNEREvaluation Protocol=Dynamic-Fewshot, Base Model=Qwen2.5-1.5B2024.09 | 49.7 | 44.1 | 44 | 43.4 | 42.9 | 48.5 | 43.1 | 43.8 | |
| PromptNEREvaluation Protocol=Dynamic-Fewshot, Base Model=GPT-4o2024.09 | 49.4 | 48.5 | 47.1 | 46.6 | 46 | 47.4 | 44.1 | 44 | |
| GPT-NEREvaluation Protocol=Dynamic-Fewshot, Base Model=GPT-4o2024.09 | 49.2 | 46.9 | 47.5 | 47.2 | 47 | 48.9 | 47.7 | 48.3 | |
| GPT-NEREvaluation Protocol=Dynamic-Supervised, Base Model=Qwen2.5-1.5B2024.09 | 47.6 | 39.7 | 38 | 37.6 | 37.3 | 41.2 | 35.7 | 36.1 | |
| PromptNEREvaluation Protocol=Dynamic-Supervised, Base Model=Qwen2.5-7B2024.09 | 44.3 | 35.8 | 33.2 | 32.5 | 31.9 | 40.4 | 37.4 | 35.6 | |
| GPT-NEREvaluation Protocol=Dynamic-Fewshot, Base Model=Qwen2.5-7B2024.09 | 42.7 | 37.3 | 38.2 | 36.8 | 36.5 | 41.1 | 37.3 | 38.6 | |
| PromptNEREvaluation Protocol=Dynamic-Fewshot, Base Model=Qwen2.5-7B2024.09 | 39.8 | 33.2 | 32.1 | 31.8 | 31.5 | 37.8 | 35.6 | 34.5 | |
| GPT-NEREvaluation Protocol=Dynamic-Fewshot, Base Model=Qwen2.5-1.5B2024.09 | 36.9 | 32.2 | 31.9 | 30.5 | 30.3 | 35.8 | 31.9 | 32.6 | |
| PromptNEREvaluation Protocol=Dynamic-Supervised, Base Model=Qwen2.5-1.5B2024.09 | 23.2 | 20.8 | 18.5 | 16.3 | 17.5 | 22.7 | 18 | 17.3 | |
| PromptNEREvaluation Protocol=Dynamic-Fewshot, Base Model=Qwen2.5-1.5B2024.09 | 20.5 | 17.9 | 16.2 | 15.9 | 16.1 | 19.9 | 16 | 15.9 |