Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Faithfulness under retraining on Kin8nm
Loading...
7.7
AURC
AXIL
2.708
4.004
5.3
6.596
Jan 5, 2023
AURC
Standard Error
Updated 5d ago
Evaluation Results
Method
Method
Links
AURC
Standard Error
AXIL
N=8,192, M=8
2023.01
7.7
0.005
BoostIn
N=8,192, M=8
2023.01
7.3
0.005
TREX
N=8,192, M=8
2023.01
6.8
0.004
Random
N=8,192, M=8
2023.01
2.9
0.001
Feedback
Search any
task
Search any
task