Why Do Some Language Models Fake Alignment While Others Don't?

NeurIPSSpotlight2025

Authors
Abhay Sheshadri, John Hughes, Julian Michael, Alex Troy Mallen, Arun Jose, Fabien Roger
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

*Alignment Faking in Large Language Models* presented a demonstration of Claude 3 Opus and Claude 3…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

large language model language model alignment

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive