logo
today local_bar

Fabien Roger

Researcher, Anthropic

3 papers at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

1 paper
Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM
Exhibit Hall C,D,E
Why Do Some Language Models Fake Alignment While Others Don't?
#1307 Spotlight · Abhay Sheshadri, John Hughes, Julian Michael, Alex Troy Mallen, Arun Jose, Fabien Roger

We analyze alignment faking propensities in 23 LLMs, and attempt to explain why some LLMs fake alignment and others don't.

Poster Session 3

1 paper
Thursday, December 4, 2025 · 11:00 AM → 2:00 PM
Exhibit Hall C,D,E
Quantifying Elicitation of Latent Capabilities in Language Models
#3606 · Elizabeth Donoway, Hailey Joren, Arushi Somani, Henry Sleight, Julian Michael, Michael R DeWeese, John Schulman, Ethan Perez, Fabien Roger, Jan Leike

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 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.