The Obfuscation Atlas: Mapping Where Honesty Emerges in RLVR with Deception Probes Paper • 2602.15515 • Published Feb 17 • 2
The Obfuscation Atlas Collection Obfuscated Policy, Obfuscated Activations, Blatant Deception, and Honest models trained in the Obfuscation Atlas paper. • 490 items • Updated Feb 20 • 1
PKU-Alignment/beaver-7b-unified-reward Reinforcement Learning • 7B • Updated Apr 20, 2024 • 1.05k • 1