Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Abstention Classification on HotPotQA (test)
Loading...
1
Abs(0)
Ternary
0.48416
0.61808
0.752
0.88592
Oct 1, 2025
Abs(0)
Delta
Updated 5d ago
Evaluation Results
Method
Method
Links
Abs(0)
Delta
Ternary
2025.10
1
0
OTC
2025.10
0.953
0.414
MASH w/ OTC
2025.10
0.948
0.523
MASH w/ EXP
2025.10
0.945
0.527
MASH w/ OTC-ST
2025.10
0.912
0.603
AFH
mode=Multisample
2025.10
0.892
0.576
DPO
2025.10
0.859
0.735
Prompting
shots=5-shot
2025.10
0.605
0.269
AFH
mode=Absolute
2025.10
0.504
0.354
Feedback
Search any
task
Search any
task