Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Factual Accuracy Estimation on Real-data Factual Qwen responses

55.94Original Accuracy

Logistic Regression

53.14354.541555.9457.3385Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
55.9456.150.21280
2026.06
55.9456.510.57280
2026.06
55.9460.154.21280
2026.06
55.9451.89-4.05280
2026.06
55.9459.233.29280
2026.06
55.9480.3124.37292.8