BriefGPT.xyz
Mar, 2024
DivTOD：发挥LLMs在多样化任务导向对话表示中的力量
DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations
HTML
PDF
Weihao Zeng, Dayuan Fu, Keqing He, Yejie Wang, Yukai Xu...
TL;DR
本文提出了一种称为DivTOD的新型对话预训练模型，它与LLMs合作，学习多样的任务导向对话表示，并在各种下游对话任务上优于强基线模型，同时学习任务导向对话的内在多样性。
Abstract
language models
pre-trained on general text have achieved impressive results in diverse fields. Yet, the distinct linguistic characteristics of
task-oriented dialogues
(TOD) compared to general text limit the pra
→