PII Detection on PII-Multi v1 (test)
0.942Entity F1 ScoreLlama3.1
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Llama3.1Model Category=Open-source Large Language Model2025.02 | 0.942 | 0.883 | 0.884 | |
| DeepSeekV3Model Category=API-based Large Language Model2025.02 | 0.927 | 0.884 | 0.886 | |
| GPT4oModel Category=API-based Large Language Model2025.02 | 0.923 | 0.891 | 0.893 | |
| Claude3.5Model Category=API-based Large Language Model2025.02 | 0.92 | 0.89 | 0.892 | |
| Qwen2.5Model Category=Open-source Large Language Model2025.02 | 0.918 | 0.853 | 0.855 | |
| Llama3.1-SLMModel Category=Open-source Small Language Model2025.02 | 0.869 | 0.778 | 0.781 | |
| BiLSTM-CRFModel Category=Traditional Model2025.02 | 0.828 | — | — | |
| Qwen2.5-SLMModel Category=Open-source Small Language Model2025.02 | 0.806 | 0.451 | 0.453 |