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

LLM Alignment on Anthropic HH-RLHF 2022 (test)

62Win Rate

MARS

50.5653.5356.559.47Feb 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
62
2026.02
52
2026.02
52
2026.02
51