Tasl: Continual dialog state tracking via task skill localization and consolidation
A practical dialogue system requires the capacity for ongoing skill acquisition and
adaptability to new tasks while preserving prior knowledge. However, current methods for …
adaptability to new tasks while preserving prior knowledge. However, current methods for …
Recurrent Knowledge Identification and Fusion for Language Model Continual Learning
Continual learning (CL) is crucial for deploying large language models (LLMs) in dynamic
real-world environments without costly retraining. While recent model ensemble and model …
real-world environments without costly retraining. While recent model ensemble and model …
Zero-shot Cross-domain Dialogue State Tracking via Context-aware Auto-prompting and Instruction-following Contrastive Decoding
Zero-shot cross-domain dialogue state tracking (DST) enables us to manage task-oriented
dialogues in new, unseen domains without the cost of collecting in-domain data. Previous …
dialogues in new, unseen domains without the cost of collecting in-domain data. Previous …
GeoEdit: Geometric Knowledge Editing for Large Language Models
Regular updates are essential for maintaining up-to-date knowledge in large language
models (LLMs). Consequently, various model editing methods have been developed to …
models (LLMs). Consequently, various model editing methods have been developed to …
Diversity-grounded Channel Prototypical Learning for Out-of-Distribution Intent Detection
In the realm of task-oriented dialogue systems, a robust intent detection mechanism must
effectively handle malformed utterances encountered in real-world scenarios. This study …
effectively handle malformed utterances encountered in real-world scenarios. This study …