PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving
The PACE is presented, a framework for retrieval-augmented dialogue serving that formalizes Perceived Time-to-First-Response (PTFR) as a QoE objective and minimizes it under quality/cost constraints and is the first quantification of filler-answer conflict risk in deployed services.
Ling Huang, Yujuan Tan, Wei-Sheng Li et al.
· 0 citations