20
Do Benign-Trained Hidden-State Probes Detect Tool Errors Under Adversarial Conditions?
arXiv:2611.11172v1 Announce Type: new Abstract: Although hidden-state probes efficiently monitor model operation, it remains unclear whether probes trained on benign tool use remain useful for detecting incorrect actions under adversarial conditions. In this research, we assess …
🅲 hạng C