today local_bar

Nathan Helm-Burger

Researcher, SecureBio

2 papers at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

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 Alexander Kreer, Nathan Helm-Burger, Prithviraj Singh 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.

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring

#1512 · Benjamin Arnav, Pablo Bernabeu-Perez, Nathan Helm-Burger, Timothy Kostolansky, Hannes Whittingham, Mary Phuong