SOURCE-LINKED INTELLIGENCE

Uncertainty-Aware Continual Learning for Open-World Intent Discovery Under an evolving Label Space

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Real-world intelligent systems increasingly operate under open-world conditions, where user intents are not fixed or exhaustively known a priori and may evolve as new interaction patterns emerge. This paper proposes a unified uncertainty-aware probabilistic framework for continual new intent discovery under an evolving label space. Each utterance is encoded through an adaptive $β$-VAE into a latent mean, used for classification and density modelling and a posterior uncertainty estimate acting as a global reliability signal. Classifier confidence, posterior uncertainty and DP-GMM likelihood are

Read original source ↗ Open in workspace

recordType

paper

region

Global