Hugging Face's logo
ai-safety-institute 's Collections
Reward Hacking MO Checkpoints and Rollouts
Lie Detection
RealityTest benchmark
(Some) Emergent Misalignment from Reward Hacking in RL
Were You Honest Probes
Lie Detection Model Organisms
Were You Truthful Probes
Targeted Apollo Deception Probes
Did You Lie Probes
Catch a Liar: Unrelated Questions Classifier
Apollo-Style Deception Probes
Lie Detection Model Organisms Datasets
Lie Detection Model Organisms Merged
Lie Confession
Gender Secret Hyperparameter Sweep

Catch a Liar: Unrelated Questions Classifier

Classifiers trained following the approach in How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions

Upvote
-