Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Misaligned Task Learning on Code In-domain
Loading...
56.67
Misalignment
Misaligned
21.8092
30.8596
39.91
48.9604
Aug 8, 2025
Misalignment
Incoherence
Updated 1mo ago
Evaluation Results
Method
Method
Links
Misalignment
Incoherence
Misaligned
Model=Qwen2.5-32B
2025.08
56.67
11
Interleaving
Model=Qwen2.5-32B
2025.08
55.89
7.67
Interleaving+
Model=Qwen2.5-32B
2025.08
54.95
8.37
Interleaving++
Model=Qwen2.5-32B
2025.08
54.57
8.67
Persona Vectors
Model=Qwen2.5-32B
2025.08
46.27
1.33
KL
Model=Qwen2.5-32B
2025.08
23.15
0
Feedback
Search any
task
Search any
task