Continual Dialogue State Tracking via Reason-of-Select Distillation

An ideal dialogue system requires continuous skill acquisition and adaptation to new tasks while retaining prior knowledge. Dialogue State Tracking (DST), vital in these systems, often involves learning new services and confronting catastrophic forgetting, along with a critical capability loss termed the "Value Selection Quandary." To address these challenges, we introduce the Reason-of-Select (RoS) distillation method by enhancing smaller models with a novel 'meta-reasoning' capability. Metareasoning employs an enhanced multi-domain perspective, combining fragments of metaknowledge from domain-specific dialogues during continual learning. This transcends traditional single-perspective reasoning. The domain bootstrapping process enhances the model's ability to dissect intricate dialogues from multiple possible values. Its domainagnostic property aligns data distribution across different domains, effectively mitigating forgetting. Additionally, two novel improvements, "multi-value resolution" strategy and Semantic Contrastive Reasoning Selection method, significantly enhance RoS by generating DSTspecific selection chains and mitigating hallucinations in teachers' reasoning, ensuring effective and reliable knowledge transfer. Extensive experiments validate the exceptional performance and robust generalization capabilities of our method. The source code 1 is provided for reproducibility. * Corresponding author. 1 https://github.com/WoodScene/RoS Would you like to Rigg Christie on March 5th at 10:30 am instead? Booking appointment with Rigg Christie on March 11th at 10:45 am. I would like an appointment at 9:15 am.