Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
LLM Steering on BASE→USER.POS (out-of-distribution)
Loading...
2.535
Steerability
L2S
1.0842
1.46085
1.8375
2.21415
Apr 4, 2026
Steerability
Proportion Steerable
Updated 12d ago
Evaluation Results
Method
Method
Links
Steerability
Proportion Steerable
L2S
Model=Llama-2-7B-Chat,...
2026.04
2.535
95
L2S
Model=Llama-2-7B-Chat,...
2026.04
2.102
92.1
CAA
Model=Llama-2-7B-Chat,...
2026.04
1.674
78.4
L2S
Model=Qwen1.5-14B-Chat...
2026.04
1.634
78.5
CAA
Model=Qwen1.5-14B-Chat...
2026.04
1.454
80.3
L2S
Model=Qwen1.5-14B-Chat...
2026.04
1.434
77.9
CAA
Model=Qwen1.5-14B-Chat...
2026.04
1.295
76.8
CAA
Model=Llama-2-7B-Chat,...
2026.04
1.14
75.3
Feedback
Search any
task
Search any
task