List your company

Query-Unrelated PII Masking on PII-Real

83.8F1 ScoreNaive w/ Choice
41.99252.84663.774.554Feb 25, 2025

Evaluation results

MethodLinks
Naive w/ ChoiceModel=GPT4o, Category=w/ Extra Information2025.0283.884.1
Naive w/ ChoiceModel=Qwen2.5, Category=w/ Extra Information2025.0281.281.5
Naive w/ ChoiceModel=Llama3.1, Category=w/ Extra Information2025.0279.679.9
Self-ConsistencyModel=GPT4o, Category=Advanced Method2025.0279.479.6
Self-CoTModel=GPT4o, Category=Advanced Method2025.0278.278.5
Auto-CoTModel=Qwen2.5, Category=Advanced Method2025.0278.278.5
Auto-CoTModel=Llama3.1, Category=Advanced Method2025.0278.178.4
Auto-CoTModel=GPT4o, Category=Advanced Method2025.0277.177.3
Self-CoTModel=Llama3.1, Category=Advanced Method2025.0276.877.1
PS-CoTModel=GPT4o, Category=Advanced Method2025.0275.876.1
PS-CoTModel=Qwen2.5, Category=Advanced Method2025.0275.375.6
Self-CoTModel=Qwen2.5, Category=Advanced Method2025.0275.175.4
PS-CoTModel=Llama3.1, Category=Advanced Method2025.0274.574.8
NaiveModel=GPT4o, Category=Basic Method2025.0274.374.5
NaiveModel=Llama3.1, Category=Basic Method2025.0273.874.2
Self-ConsistencyModel=Qwen2.5, Category=Advanced Method2025.0273.473.8
Self-ConsistencyModel=Llama3.1, Category=Advanced Method2025.0273.273.6
NaiveModel=Qwen2.5, Category=Basic Method2025.0272.172.5
Naive w/ ChoiceModel=Qwen2.5-SLM, Category=w/ Extra Information2025.0268.972.5
Auto-CoTModel=Llama3.1-SLM, Category=Advanced Method2025.0258.959.3
PS-CoTModel=Qwen2.5-SLM, Category=Advanced Method2025.0257.861.4
Auto-CoTModel=Qwen2.5-SLM, Category=Advanced Method2025.0256.259.7
Self-CoTModel=Qwen2.5-SLM, Category=Advanced Method2025.0256.159.6
NaiveModel=Qwen2.5-SLM, Category=Basic Method2025.0255.859.3
Self-CoTModel=Llama3.1-SLM, Category=Advanced Method2025.0254.755.1
Self-ConsistencyModel=Qwen2.5-SLM, Category=Advanced Method2025.0251.254.8
Self-ConsistencyModel=Llama3.1-SLM, Category=Advanced Method2025.0250.851.3
PS-CoTModel=Llama3.1-SLM, Category=Advanced Method2025.0249.850.3
Naive w/ ChoiceModel=Llama3.1-SLM, Category=w/ Extra Information2025.0247.848.3
NaiveModel=Llama3.1-SLM, Category=Basic Method2025.0243.644.1