OREGON STATE UNIVERSITY

You are here

Too much, too little, or just right? Ways explanations impact end users' mental models

TitleToo much, too little, or just right? Ways explanations impact end users' mental models
Publication TypeConference Paper
Year of Publication2013
AuthorsKulesza, T., S. Stumpf, M. Burnett, S. Yang, I. Kwan, and W-K. Wong
Conference Name2013 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC)
Pagination3 - 10
Date Published09/2013
PublisherIEEE
Conference LocationSan Jose, CA
Abstract

Research is emerging on how end users can correct mistakes their intelligent agents make, but before users can correctly “debug” an intelligent agent, they need some degree of understanding of how it works. In this paper we consider ways intelligent agents should explain themselves to end users, especially focusing on how the soundness and completeness of the explanations impacts the fidelity of end users' mental models. Our findings suggest that completeness is more important than soundness: increasing completeness via certain information types helped participants' mental models and, surprisingly, their perception of the cost/benefit tradeoff of attending to the explanations. We also found that oversimplification, as per many commercial agents, can be a problem: when soundness was very low, participants experienced more mental demand and lost trust in the explanations, thereby reducing the likelihood that users will pay attention to such explanations at all.

DOI10.1109/VLHCC.2013.6645235