ChatrEx: Designing Explainable Chatbot Interfaces for Enhancing Usefulness, Transparency, and Trust

Authors

Anjali Khurana, Parsa Alamzadeh, Parmit K. Chilana

Research Lab

Parmit Chilana

Research Themes

In-context Help

Explainable AI

Abstract

When breakdowns occur during a human-chatbot conversation, the lack of transparency and the “black-box” nature of task-oriented chatbots can make it difficult for end users to understand what went wrong and why. Inspired by recent HCI research on explainable AI solutions, we explored the design of in-application explainable chatbot interfaces (ChatrEx) that explain the underlying working of a chatbot during a breakdown. ChatrEx-VINC provides visual example-based step-by-step explanations in-context of the chat window whereas ChatrEx-VST provides explanations as a visual tour overlaid on the application interface. We implemented these chatbots for complex spreadsheet tasks and our comparative observational study (N=14) showed that the explanations provided by both ChatrEx-VINC and ChatrEx-VST enhanced users’ understanding of the reasons for a breakdown and improved users’ perceptions of usefulness, transparency, and trust. We identify several opportunities for future research to exploit explainable chatbot interfaces and better support human-chatbot interaction.

Citation

Anjali Khurana, Parsa Alamzadeh ,and Parmit K. Chilana. "ChatrEx: Designing Explainable Chatbot Interfaces for Enhancing Usefulness, Transparency, and Trust" Proceedings of the IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC 21), to appear [30% acceptance rate]