Morality in dialogue systems has raised great attention in research recently. A moral dialogue system aligned with users' values could enhance conversation engagement and user connections. In this paper, we propose a framework, MoralDial to train and evaluate moral dialogue systems. In our framework, we first explore the communication mechanisms of morality and resolve expressed morality into three parts, which indicate the roadmap for building a moral dialogue system. Based on that, we design a simple yet effective method: constructing moral discussions between simulated specific users and the dialogue system. The constructed discussions consist of expressing, explaining, revising, and inferring moral views in dialogue exchanges, which makes conversational models learn morality well in a natural manner. Furthermore, we propose a novel evaluation method under the framework. We evaluate the multiple aspects of morality by judging the relation between dialogue responses and human values in discussions, where the multifaceted nature of morality is particularly considered. Automatic and manual experiments demonstrate that our framework is promising to train and evaluate moral dialogue systems.

翻译：对话系统中的道德问题近期引起了研究界的广泛关注。与用户价值观相一致的道德对话系统能够增强对话参与度并加强用户联系。本文提出了一种名为MoralDial的框架，用于训练与评估道德对话系统。在该框架中，我们首先探究道德的沟通机制，将表达出的道德观念解析为三个组成部分，这为构建道德对话系统指明了方向。基于此，我们设计了一种简单有效的方法：在模拟特定用户与对话系统之间构建道德讨论。这些讨论包含对话交互中道德观点的表达、解释、修正与推理，使对话模型能够以自然的方式良好地学习道德规范。此外，我们在该框架下提出了一种新颖的评估方法。通过判断讨论中对话响应与人类价值观之间的关系，我们特别考虑了道德的多面性，对道德的多个维度进行评估。自动实验与人工实验表明，本框架在训练与评估道德对话系统方面具有良好前景。