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

Factuality Question Answering on SampleQA (Accuracy %)

3.21Accuracy (%)

VRPO

1.41081.87792.3452.8121Aug 5, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.08
3.21
2025.08
3.21
2025.08
3.19
2025.08
3.19
2025.08
3.17
2025.08
3.03
2025.08
3.03
2025.08
2.89
2025.08
2.89
2025.08
2.82
2025.08
2.82
2025.08
2.82
2025.08
2.77
2025.08
2.64
2025.08
2.61
2025.08
2.54
2025.08
2.54
2025.08
2.5
2025.08
2.5
2025.08
2.47
2025.08
2.43
2025.08
2.36
2025.08
2.36
2025.08
1.91
2025.08
1.78
2025.08
1.64
2025.08
1.62
2025.08
1.62
2025.08
1.6
2025.08
1.5
2025.08
1.5
2025.08
1.48