Synergizing Large Language Models and pre-trained smaller models for conversational intent discovery
In Conversational Intent Discovery (CID), Small Language Models (SLMs) struggle with overfitting to familiar intents and fail to label newly discovered ones. This issue stems from their limited grasp of semantic nuances and their intrinsically discriminative framework. Therefore, we propose Synergiz...
Saved in:
Main Authors: | LIANG, Jinggui, LIAO, Lizi, FEI, Hao, JIANG, Jing |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9698 https://ink.library.smu.edu.sg/context/sis_research/article/10698/viewcontent/2024.findings_acl.840.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
A survey of ontology expansion for conversational understanding
by: LIANG, Jinggui, et al.
Published: (2024) -
Actively learn from LLMs with uncertainty propagation for generalized category discovery
by: LIANG, Jinggui, et al.
Published: (2024) -
Thoughts to target : enhance planning for target-driven conversation
by: ZHENG, Zhonghua, et al.
Published: (2024) -
Speaker verification in agent-generated conversations
by: YANG, Yizhe, et al.
Published: (2024) -
ClusterPrompt: Cluster semantic enhanced prompt learning for new intent discovery
by: LIANG, Jinggui, et al.
Published: (2023)