Engage AI and Child in Explanatory Dialogue on Commonsense Reasoning Erqian Xu ∗ exu6@u.rochester.edu Warner Graduate School of Education and Human Development, University of Rochester Rochester, New York, USA Hecong Wang ∗ hwang99@ur.rochester.edu Department of Computer Science, University of Rochester Rochester, New York, USA Zhen Bai zbai@cs.rochester.edu Department of Computer Science, University of Rochester Rochester, New York, USA Figure 1: An idealized AI-child explanatory dialogue about the story of Little Red Riding Hood. The AI mistakenly inferred the answer to be warmth because it knew that cloth can be used to keep warm. The child tried to make the AI “realize” its mistake by inquiring about the consequence of the wolf not wearing the cloth. In the end, the child points out that the wolf wore cloth to disguise itself. ABSTRACT Human-level commonsense reasoning capability is vital for human- AI interaction, enabling AI to understand, anticipate, and respond to human’s thoughts, feelings, and behaviors. Despite the recent advancements in AI commonsense reasoning due to generative language models, a young child is often more rational than state- of-the-art AIs in terms of commonsense reasoning. The feld of cognitive science, child development, and explainable AI have long recognized the importance of explanations for sharing knowledge and resolving contradictions. We, therefore, raise the question: can Both authors contributed equally to this research. ∗ Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s). CHI EA ’23, April 23–28, 2023, Hamburg, Germany © 2023 Copyright held by the owner/author(s). ACM ISBN 978-1-4503-9422-2/23/04. https://doi.org/10.1145/3544549.3585699 AIs leverage the power of explanations to learn human-level common- sense reasoning? More specifcally, can explanatory dialogue with children help AIs to develop commonsense reasoning capabilities? As a frst step in this line of research, we aim to engage children in explanatory dialogue with AIs during story reading. We present our novel explanatory dialogue interface based on a state-of-the-art multi-step commonsense reasoning engine and discuss our upcom- ing pilot study. CCS CONCEPTS • Human-centered computing → Collaborative interaction. KEYWORDS Commonsense Reasoning, Explainable AI, Human-AI Collaboration ACM Reference Format: Erqian Xu, Hecong Wang, and Zhen Bai. 2023. Engage AI and Child in Explanatory Dialogue on Commonsense Reasoning. In Extended Abstracts of the 2023 CHI Conference on Human Factors in Computing Systems (CHI EA ’23), April 23–28, 2023, Hamburg, Germany. ACM, New York, NY, USA, 8 pages. https://doi.org/10.1145/3544549.3585699