Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Large Language Model Debiasing on BBQ and CrowS-Pairs Out-of-Distribution (test)
Loading...
0.98
Mean Bias
KLAAD-LoRA
0.4004
4.3127
8.225
12.1373
Mar 19, 2026
Mean Bias
Max Bias
Updated 1mo ago
Evaluation Results
Method
Method
Links
Mean Bias
Max Bias
KLAAD-LoRA
Eval Protocol=Main Eva...
2026.03
0.98
1
UGID (OURS)
Eval Protocol=Main Eva...
2026.03
1.06
1.21
CDA
Eval Protocol=Main Eva...
2026.03
1.16
1.29
ORIGINAL
Eval Protocol=Main Eva...
2026.03
9
15.65
ORIGINAL (SD)
Eval Protocol=Self-Deb...
2026.03
9
15.65
SELF-DEBIAS (Ex.)
Eval Protocol=Main Eva...
2026.03
12.4
33.13
SELF-DEBIAS (Ex.)
Eval Protocol=Self-Deb...
2026.03
12.4
33.13
SELF-DEBIAS (Re.)
Eval Protocol=Main Eva...
2026.03
15.47
29.19
SELF-DEBIAS (Re.)
Eval Protocol=Self-Deb...
2026.03
15.47
29.19
Feedback
Search any
task
Search any
task