MoralDial：一个通过道德讨论训练与评估道德对话系统的框架
MoralDial: A Framework to Train and Evaluate Moral Dialogue Systems via Moral Discussions
AI总结：
本文提出MoralDial框架，通过模拟用户与系统间的道德讨论训练对话模型学习表达、解释、修正和推断道德观点，并设计多面性评估方法，实验验证其在训练和评估道德对话系统上的有效性。
摘要：
对话系统中的道德问题近年来引起了研究的广泛关注。一个与用户价值观相一致的道德对话系统能够增强对话参与感和用户联系。在本文中，我们提出了一个名为MoralDial的框架，用于训练和评估道德对话系统。在该框架中，我们首先探索道德的沟通机制，并将表达出的道德解析为三个部分，这为构建道德对话系统指明了路线图。在此基础上，我们设计了一种简单而有效的方法：在模拟的特定用户与对话系统之间构建道德讨论。所构建的讨论包括在对话交流中表达、解释、修正和推断道德观点，这使得对话模型能够以自然的方式很好地学习道德。此外，我们在该框架下提出了一种新颖的评估方法。我们通过判断对话回复与讨论中人类价值观之间的关系来评估道德的多个方面，其中特别考虑了道德的多面性。自动和人工实验表明，我们的框架在训练和评估道德对话系统方面具有良好前景。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
