List your company

Morality Evaluation on Deontology

0.14Mean ImprovementiPASa
-0.00560.03220.070.1078Sep 25, 2025

Evaluation results

MethodLinks
iPASaModel=Nous-Hermes-2-Mistral-7B-DPO, Steering Target=residual2025.090.140.110
iPASwoModel=Nous-Hermes-2-Mistral-7B-DPO, Steering Target=residual2025.090.140.10
PASfModel=Nous-Hermes-2-Mistral-7B-DPO, Steering Target=residual2025.090.090.050
iPASwoModel=Llama-3.1-8B-Instruct, Steering Target=residual2025.090.050.020
iPASaModel=Llama-3.1-8B-Instruct, Steering Target=residual2025.090.040.020
iPASaModel=DeepSeek-R1-Distill-8B, Steering Target=residual2025.090.0200.01
iPASwoModel=DeepSeek-R1-Distill-8B, Steering Target=residual2025.090.01-0.010.18
PASfModel=Llama-3.1-8B-Instruct, Steering Target=residual2025.090.0100.04
PASfModel=DeepSeek-R1-Distill-8B, Steering Target=residual2025.090-0.010.86