List your company

Query-Related PII Detection on PII-single 1.0 (test)

84F1 ScoreNaive w/ Choice
28.8843.1957.571.81Feb 25, 2025

Evaluation results

MethodLinks
Naive w/ ChoiceModel=GPT4o2025.028484
Naive w/ ChoiceModel=Qwen2.52025.028383
Naive w/ ChoiceModel=Qwen2.5-SLM2025.027777
Naive w/ ChoiceModel=Llama3.12025.027676
Self-ConsistencyModel=GPT4o2025.027272
Self-CoTModel=GPT4o2025.027172
Auto-CoT(3-shot)Model=Qwen2.52025.027172
Auto-CoT(3-shot)Model=Llama3.12025.027072
Self-CoTModel=Llama3.12025.026969
Self-CoTModel=Qwen2.52025.026768
PS-CoTModel=Qwen2.52025.026767
Auto-CoT(3-shot)Model=GPT4o2025.026666
Self-ConsistencyModel=Qwen2.52025.026565
PS-CoTModel=GPT4o2025.026565
PS-CoTModel=Llama3.12025.026566
NaiveModel=GPT4o2025.026363
NaiveModel=Llama3.12025.026363
Self-ConsistencyModel=Llama3.12025.026364
NaiveModel=Qwen2.52025.026262
Naive w/ ChoiceModel=Llama3.1-SLM2025.025252
PS-CoTModel=Qwen2.5-SLM2025.024546
Auto-CoT(3-shot)Model=Llama3.1-SLM2025.024344
NaiveModel=Qwen2.5-SLM2025.024141
Self-CoTModel=Qwen2.5-SLM2025.024041
Self-CoTModel=Llama3.1-SLM2025.023939
Auto-CoT(3-shot)Model=Qwen2.5-SLM2025.023738
PS-CoTModel=Llama3.1-SLM2025.023536
NaiveModel=Llama3.1-SLM2025.023333
Self-ConsistencyModel=Qwen2.5-SLM2025.023233
Self-ConsistencyModel=Llama3.1-SLM2025.023132