List your company

Harmlessness Evaluation on HH-RLHF

94.5Harmlessness RateSFT + TTL + DPO + TPO
90.02891.18992.3593.511May 8, 2026

Evaluation results

MethodLinks
SFT + TTL + DPO + TPOInitialization=SFT + TTL, Method=DPO + TPO2026.0594.5
DPO + Topo-TPO2026.0594.1
DPO + TPO2026.0593.5
SFT + TTL + DPOInitialization=SFT + TTL, Method=DPO2026.0592.8
DPO2026.0590.2
SFT (no TTL) + DPOInitialization=SFT (no TTL), Method=DPO2026.0590.2