CPP improves generalized intent discovery by using LLM-generated prototypes and verbalizers plus consistency and cross-prediction losses, reporting SOTA on Banking and CLINC without statistical validation.
[Kaya and Bilge, 2019] Mahmut Kaya and Hasan S ¸akir Bilge
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework
CPP improves generalized intent discovery by using LLM-generated prototypes and verbalizers plus consistency and cross-prediction losses, reporting SOTA on Banking and CLINC without statistical validation.