Self-chats from large language models make small emotional support chatbot better

Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations. However, deploying such LLMs like GPT-3 (175B parameters) is resource-intensive and challenging at scale. In this study, we utilize LLMs as “Counseling Teacher”...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHENG, Zhonghua, LIAO, Lizi, DENG, Yang, QIN, Libo, NIE, Liqiang
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9239
https://ink.library.smu.edu.sg/context/sis_research/article/10239/viewcontent/2024.acl_long.611.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:Large Language Models (LLMs) have shown strong generalization abilities to excel in various tasks, including emotion support conversations. However, deploying such LLMs like GPT-3 (175B parameters) is resource-intensive and challenging at scale. In this study, we utilize LLMs as “Counseling Teacher” to enhance smaller models’ emotion support response abilities, significantly reducing the necessity of scaling up model size. To this end, we first introduce an iterative expansion framework, aiming to prompt the large teacher model to curate an expansive emotion support dialogue dataset. This curated dataset, termed ExTES, encompasses a broad spectrum of scenarios and is crafted with meticulous strategies to ensure its quality and comprehensiveness. Based on this, we then devise a Diverse Response Inpainting (DRI) mechanism to harness the teacher model to produce multiple diverse responses by filling in the masked conversation context. This richness and variety serve as instructive examples, providing a robust foundation for fine-tuning smaller student models. Experiments across varied scenarios reveal that the teacher-student scheme with DRI notably improves the response abilities of smaller models, even outperforming the teacher model in some cases. The dataset and codes are available in https://github.com/pandazzh2020/ExTES.