logo
today local_bar
Deception Detection

1 paper across 1 session

Poster Session 4

1 paper
Thursday, December 4, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
#1517 · Cameron Tice, Philipp Kreer, Nathan Helm-Burger, Prithviraj Shahani, Fedor Ryzhenkov, Fabien Roger, Clement Neo, Jacob Haimes, Felix Hofstätter, Teun van der Weij

We introduce a novel method leveraging noise injection as a tool to elicit the latent capabilities of sandbagging LLMs.