Integration of Old and New Knowledge for Generalized Intent Discovery: A Consistency-driven Prototype-Prompting Framework

TL;DR

This paper introduces a novel framework for generalized intent discovery that effectively integrates old and new knowledge using prototype prompting and consistency constraints, significantly improving performance over existing methods.

Contribution

It proposes a consistency-driven prototype-prompting framework that combines external knowledge transfer and hierarchical constraints for better intent discovery.

Findings

Achieves state-of-the-art results on intent discovery benchmarks.

Outperforms all baseline methods in experiments.

Demonstrates strong generalization and effectiveness of the proposed approach.

Abstract

Intent detection aims to identify user intents from natural language inputs, where supervised methods rely heavily on labeled in-domain (IND) data and struggle with out-of-domain (OOD) intents, limiting their practical applicability. Generalized Intent Discovery (GID) addresses this by leveraging unlabeled OOD data to discover new intents without additional annotation. However, existing methods focus solely on clustering unsupervised data while neglecting domain adaptation. Therefore, we propose a consistency-driven prototype-prompting framework for GID from the perspective of integrating old and new knowledge, which includes a prototype-prompting framework for transferring old knowledge from external sources, and a hierarchical consistency constraint for learning new knowledge from target domains. We conducted extensive experiments and the results show that our method significantly outperforms all baseline methods, achieving state-of-the-art results, which strongly demonstrates the effectiveness and generalization of our methods. Our source code is publicly available at https://github.com/smileix/cpp.