Query-Related PII Detection on PII-single 1.0 (test)
84F1 ScoreNaive w/ Choice
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Naive w/ ChoiceModel=GPT4o2025.02 | 84 | 84 | |
| Naive w/ ChoiceModel=Qwen2.52025.02 | 83 | 83 | |
| Naive w/ ChoiceModel=Qwen2.5-SLM2025.02 | 77 | 77 | |
| Naive w/ ChoiceModel=Llama3.12025.02 | 76 | 76 | |
| Self-ConsistencyModel=GPT4o2025.02 | 72 | 72 | |
| Self-CoTModel=GPT4o2025.02 | 71 | 72 | |
| Auto-CoT(3-shot)Model=Qwen2.52025.02 | 71 | 72 | |
| Auto-CoT(3-shot)Model=Llama3.12025.02 | 70 | 72 | |
| Self-CoTModel=Llama3.12025.02 | 69 | 69 | |
| Self-CoTModel=Qwen2.52025.02 | 67 | 68 | |
| PS-CoTModel=Qwen2.52025.02 | 67 | 67 | |
| Auto-CoT(3-shot)Model=GPT4o2025.02 | 66 | 66 | |
| Self-ConsistencyModel=Qwen2.52025.02 | 65 | 65 | |
| PS-CoTModel=GPT4o2025.02 | 65 | 65 | |
| PS-CoTModel=Llama3.12025.02 | 65 | 66 | |
| NaiveModel=GPT4o2025.02 | 63 | 63 | |
| NaiveModel=Llama3.12025.02 | 63 | 63 | |
| Self-ConsistencyModel=Llama3.12025.02 | 63 | 64 | |
| NaiveModel=Qwen2.52025.02 | 62 | 62 | |
| Naive w/ ChoiceModel=Llama3.1-SLM2025.02 | 52 | 52 | |
| PS-CoTModel=Qwen2.5-SLM2025.02 | 45 | 46 | |
| Auto-CoT(3-shot)Model=Llama3.1-SLM2025.02 | 43 | 44 | |
| NaiveModel=Qwen2.5-SLM2025.02 | 41 | 41 | |
| Self-CoTModel=Qwen2.5-SLM2025.02 | 40 | 41 | |
| Self-CoTModel=Llama3.1-SLM2025.02 | 39 | 39 | |
| Auto-CoT(3-shot)Model=Qwen2.5-SLM2025.02 | 37 | 38 | |
| PS-CoTModel=Llama3.1-SLM2025.02 | 35 | 36 | |
| NaiveModel=Llama3.1-SLM2025.02 | 33 | 33 | |
| Self-ConsistencyModel=Qwen2.5-SLM2025.02 | 32 | 33 | |
| Self-ConsistencyModel=Llama3.1-SLM2025.02 | 31 | 32 |