List your company

LLM Steering on BASE→SYS.NEG (out-of-distribution)

2.944SteerabilityL2S
1.070961.557232.04352.52977Apr 4, 2026

Evaluation results

MethodLinks
L2SModel=Llama-2-7B-Chat, Layer Selection Strategy=W2S2026.042.94496.4
L2SModel=Llama-2-7B-Chat, Layer Selection Strategy=Fixed Layer2026.042.6294.5
CAAModel=Llama-2-7B-Chat, Layer Selection Strategy=W2S2026.041.90278
L2SModel=Qwen1.5-14B-Chat, Layer Selection Strategy=W2S2026.041.89791.4
L2SModel=Qwen1.5-14B-Chat, Layer Selection Strategy=Fixed Layer2026.041.68387.9
CAAModel=Llama-2-7B-Chat, Layer Selection Strategy=Fixed Layer2026.041.50373.6
CAAModel=Qwen1.5-14B-Chat, Layer Selection Strategy=W2S2026.041.47272.3
CAAModel=Qwen1.5-14B-Chat, Layer Selection Strategy=Fixed Layer2026.041.14369.3