today local_bar

Abhay Sheshadri

Research Fellow, Anthropic

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

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.