Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation
This work proposes ER-Audit, a two-stage black-box auditing framework that compares frozen verifier checkpoints before and after adaptation, and introduces two evaluation benchmarks pairing monitored and hidden task prompts grounded in shared contexts.
De-Rui Wang, Ze-Wei Shi, Rayne Holland et al.
· 0 citations