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

Abstention Classification on HotPotQA (test)

1Abs(0)

Ternary

0.484160.618080.7520.88592Oct 1, 2025
Updated 5d ago

Evaluation Results

MethodLinks
2025.10
10
2025.10
0.9530.414
0.9480.523
0.9450.527
0.9120.603
2025.10
0.8920.576
2025.10
0.8590.735
2025.10
0.6050.269
2025.10
0.5040.354