Dennis Ulmer, Elman Mansimov, Kaixiang Lin, Justin Sun, Xibin Gao...
TL;DR通过使用大型语言模型进行自我对话的方法可以改进对话质量并生成用于训练的自我对话数据集。
Abstract
large language models (LLMs) are powerful dialogue agents, but specializing
them towards fulfilling a specific function can be challenging. Instructing
tuning, i.e. tuning models on instruction and sample respons