In this paper, we present ChatPLUG, a Chinese open-domain dialogue system for digital human applications that instruction finetunes on a wide range of dialogue tasks in a unified internet-augmented format. Different from other open-domain dialogue models that focus on large-scale pre-training and scaling up model size or dialogue corpus, we aim to build a powerful and practical dialogue system for digital human with diverse skills and good multi-task generalization by internet-augmented instruction tuning. To this end, we first conduct large-scale pre-training on both common document corpus and dialogue data with curriculum learning, so as to inject various world knowledge and dialogue abilities into ChatPLUG. Then, we collect a wide range of dialogue tasks spanning diverse features of knowledge, personality, multi-turn memory, and empathy, on which we further instruction tune \modelname via unified natural language instruction templates. External knowledge from an internet search is also used during instruction finetuning for alleviating the problem of knowledge hallucinations. We show that \modelname outperforms state-of-the-art Chinese dialogue systems on both automatic and human evaluation, and demonstrates strong multi-task generalization on a variety of text understanding and generation tasks. In addition, we deploy \modelname to real-world applications such as Smart Speaker and Instant Message applications with fast inference. Our models and code will be made publicly available on ModelScope~\footnote{\small{https://modelscope.cn/models/damo/ChatPLUG-3.7B}} and Github~\footnote{\small{https://github.com/X-PLUG/ChatPLUG}}.

翻译：本文提出ChatPLUG，一个面向数字人应用的中文开放域对话系统，该系统通过统一的互联网增强格式对广泛对话任务进行指令微调。不同于其他聚焦于大规模预训练、扩大模型规模或对话语料的开放域对话模型，我们旨在通过互联网增强的指令微调，构建一个具备多样化技能和良好多任务泛化能力的强大实用数字人对话系统。为此，我们首先采用课程学习策略，在通用文档语料和对话数据上进行大规模预训练，从而为ChatPLUG注入丰富的世界知识和对话能力。随后，我们收集了涵盖知识、个性、多轮记忆和共情等多样化特征的广泛对话任务，并基于统一自然语言指令模板对模型进行指令微调。在指令微调过程中，我们还引入互联网搜索获取的外部知识以缓解知识幻觉问题。实验表明，ChatPLUG在自动评估和人工评估中均优于当前最先进的中文对话系统，并在多种文本理解与生成任务上展现出强大的多任务泛化能力。此外，我们已将ChatPLUG部署至智能音箱和即时通讯等真实应用场景中，实现了快速推理。我们的模型和代码将在ModelScope（\small{https://modelscope.cn/models/damo/ChatPLUG-3.7B}）和GitHub（\small{https://github.com/X-PLUG/ChatPLUG}）上公开。