Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors

arXiv cs.AIOctober 23, 2026en

arXiv:2610.30582v1 Announce Type: new Abstract: 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 avoids relying on a weaker reviewer the model could outsmart, but risks collusion: the model, now monitoring itself, may cover up its own misbehaviour. One remedy is to fine-tune the monitor on whatever examples of misbehaviour the control team has caught. We ask whether this training also removes collusion that the control team has not yet found. We fine-tune Llama-3.3-70B and Qwen2.5-72B to install five policy-monitor behaviour pairs, correct the monitor on 300 hon

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Meta
• Verktyg
• Forskning
• Reglering