SOTAVerified

Intent Discovery

Given a set of labelled and unlabelled utterances, the idea is to identify existing (known) intents and potential (new intents) intents. This method can be utilised in conversational system setting.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 42 papers

TitleStatusHype
Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting FrameworkCode0
From Intent Discovery to Recognition with Topic Modeling and Synthetic Data—0
LANID: LLM-assisted New Intent DiscoveryCode0
Dial-In LLM: Human-Aligned LLM-in-the-loop Intent Clustering for Customer Service Dialogues—0
IntentGPT: Few-shot Intent Discovery with Large Language Models—0
KULCQ: An Unsupervised Keyword-based Utterance Level Clustering Quality Metric—0
Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents—0
Pseudo-Label Enhanced Prototypical Contrastive Learning for Uniformed Intent DiscoveryCode0
Assured Automatic Programming via Large Language Models—0
A Survey of Ontology Expansion for Conversational Understanding—0
Show:102550
← PrevPage 1 of 5Next →
All datasetsATISPersian-ATISSNIPS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1k-PCA + HDBSCANARI59.23—Unverified