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

1 citations · 1 across the 2 of their papers we have counts for

collaborators
Showing cs.AIShow all

2 papers · 1 filter

cs.AI2026

Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors

Juan-Pablo Rivera, Ari Spiesberger, Juan J Vazquez +6

AI control protocols aim to get useful work from models that may be misaligned by monitoring their behaviour. One approach uses a second copy of the same model as the monitor. This…

cs.AI2026

Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hacking

Arun Jose, Julian Stastny

Recent work shows that models that learn to reward hack on RL environments can become broadly misaligned, and that reframing reward hacking as acceptable behavior during training (…