What is it about?
When AI chatbots make mistakes, how they apologize matters. We studied which apology styles (brief, empathic, or explanatory) people prefer across different errors, showing that effective apologies depend on context and user expectations.
Featured Image
Photo by Nick Fewings on Unsplash
Why is it important?
This work is timely because it shows that apology style matters: different errors call for different responses. The findings offer practical guidance for designing AI that repairs trust responsibly.
Perspectives
This project was especially meaningful to me because it brought together perspectives from philosophy, psychology, HCI, and AI. Working across disciplines shaped how we framed apology, not just as a system behavior, but as a moral, social, and human experience.
Zahra Ashktorab
Read the Original
This page is a summary of: Who’s Sorry Now: User Preferences Among Rote, Empathic, and Explanatory Apologies from LLM Chatbots, ACM Transactions on Computer-Human Interaction, January 2026, ACM (Association for Computing Machinery),
DOI: 10.1145/3793679.
You can read the full text:
Contributors
The following have contributed to this page
