Developing a natural language-based AI-chatbot for social work training: an illustrative case study

A chatbot is a computer program designed to simulate conversation with human users. In social services, many chatbots are retrieval based: they analyse users’ intents and retrieve preset answers based on decision tree logic. A major limitation of these earlier chatbots was that their conversations were rigid, unnatural, and sounded like a multiple-choice questionnaire. Recent achievements in large-scale generative pretrained transformers (LGPTs) (e.g. GPT-3, Yuan 1.0) have offered new possibilities for chatbot development. Such technology provides a high-quality natural language experience, requires much less resource input than earlier chatbot technologies, and is much more accessible to the public. However, the use of LGPT-based cfhatbots in social work, particularly in a Chinese context, is uncommon or even absent. Using an illustrative case study, this article illustrates the initial development of an LGPT-based chatbot to support social work training in a Chinese context and discusses the possibilities for further development.

聊天机器人是一种旨在模拟与人类用户对话的电脑程序。 在社会服务中, 许多聊天机器人也是基于检索的:它们分析用户意图并根据决策树逻辑检索预设答案。 这些早期聊天机器人的一个主要局限是它们的对话生硬、不自然, 而且听起来像是多项选择题。 最新发展的基于transformer结构的大规模生成式预训练模型 (例如 GPT-3, Yuan 1.0) 为聊天机器人的开发提供了新的可能性。 这种技术提供了高质量的自然语言体验, 比早期的聊天机器人技术需要更少的资源投入, 并且更容易为公众所接受。 然而, 在社会工作中, 特别是在中文语境中, 从业者鲜有甚至没有使用这种技术开发聊天机器人。 本文使用一个说明性案例研究, 说明了如何初步开发基于大规模生成式预训练模型的聊天机器人, 以支持中文语境中的社会工作培训, 并讨论了其进一步发展的可能性。