Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations
Paper • 2605.27958 • Published • 2 •
2
Sachin Kumar
techsachin
AI & ML interests
Generative AI,NLP
Recent Activity
commentedon a paper 1 day ago
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations submitted a paper 1 day ago
Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations authored a paper 8 months ago
Overriding Safety protections of Open-source ModelsOrganizations
None yet
commented a
paper 1 day ago
submitted a
paper to Daily Papers 1 day ago
authored a
paper 8 months ago