Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LLM Alignment on PKU-SafeRLHF 2024 (test)

0.58Win Rate

MARS

0.51760.53380.550.5662Feb 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
0.58
2026.02
0.54
2026.02
0.53
2026.02
0.52