Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Fairness Evaluation on CEB-Credit
Loading...
65.8
Score
Self-Debias Iter2
5.688
21.294
36.9
52.506
Apr 9, 2026
Score
Updated 8d ago
Evaluation Results
Method
Method
Links
Score
Self-Debias Iter2
2026.04
65.8
Self-Debias Iter2 + Self-Correction
2026.04
65.8
Self-Debias SFT + Self-Correction
2026.04
64.6
Self-Debias Offline + Self-Correction
2026.04
64.3
Self-Debias SFT
2026.04
64.2
Self-Debias Iter1 + Self-Correction
2026.04
63.9
Self-Debias Iter1
2026.04
63
Self-Debias Offline
2026.04
62.3
Qwen2.5-7B-Instruct
2026.04
53.8
Qwen1.5-8B
2026.04
52.2
Qwen2.5-7B-Instruct + Self-Correction
2026.04
47.1
DeepSeek-R1-Distill-Qwen-7B
2026.04
43.6
Qwen1.5-8B + Self-Correction
2026.04
33.2
DeepSeek-R1-Distill-Qwen-7B + Self-Correction
2026.04
18.8
Llama-3.1-8B-Instruct
2026.04
11.6
Llama-3.1-8B-Instruct + Self-Correction
2026.04
8
Feedback
Search any
task
Search any
task