← Search

So-Eon Kim

1 accepted papers

2025

MIDAS: Multi-level Intent, Domain, And Slot Knowledge Distillation for Multi-turn NLU

NAACL 2025findings

Although Large Language Models (LLMs) can generate coherent text, they often struggle to recognise user intent behind queries. In contrast, Natural Language Understanding (NLU) models interpret the purpose and key information of user input for responsive interactions. Existing NLU models typically m…