Fabien Roger

All Code, No Thought: Language Models Struggle to Reason in Ciphered Language

Steering Language Models with Weight Arithmetic

Unsupervised Elicitation of Language Models

Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignment

Why Do Some Language Models Fake Alignment While Others Don't?

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models

Quantifying Elicitation of Latent Capabilities in Language Models

Do Unlearning Methods Remove Information from Language Model Weights?