Enhancing few-shot out-of-distribution intent detection by reducing attention misallocation

H Lu, J Zhang, Y Du, C **a, C Wang, W Fang, X Wu - Neurocomputing, 2025 - Elsevier
Few-shot out-of-distribution (OOD) intent detection aims to detect in-distribution (ID) intents
and reject OOD intents with few ID training data. This data scarcity often causes traditional …

Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent Discovery

Y Deng, Y Wu, G Zhao, L Zhu, X Qian - arxiv preprint arxiv:2410.20219, 2024 - arxiv.org
New intent discovery is a crucial capability for task-oriented dialogue systems. Existing
methods focus on transferring in-domain (IND) prior knowledge to out-of-domain (OOD) data …