How Do People Rank Multiple Mutant Agents?

Jonathan Dodge, Andrew A. Anderson, Matthew Olson, Rupika Dikkala, Margaret Burnett

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

Faced with several AI-powered sequential decision-making systems, how might someone choose on which to rely? For example, imagine car buyer Blair shopping for a self-driving car, or developer Dillon trying to choose an appropriate ML model to use in their application. Their first choice might be infeasible (i.e., too expensive in money or execution time), so they may need to select their second or third choice. To address this question, this paper presents: 1) Explanation Resolution, a quantifiable direct measurement concept; 2) a new XAI empirical task to measure explanations: "the Ranking Task"; and 3) a new strategy for inducing controllable agent variations - Mutant Agent Generation. In support of those main contributions, it also presents 4) novel explanations for sequential decision-making agents; 5) an adaptation to the AAR/AI assessment process; and 6) a qualitative study around these devices with 10 participants to investigate how they performed the Ranking Task on our mutant agents, using our explanations, and structured by AAR/AI. From an XAI researcher perspective, just as mutation testing can be applied to any code, mutant agent generation can be applied to essentially any neural network for which one wants to evaluate an assessment process or explanation type. As to an XAI user's perspective, the participants ranked the agents well overall, but showed the importance of high explanation resolution for close differences between agents. The participants also revealed the importance of supporting a wide diversity of explanation diets and agent "test selection"strategies.

Original languageEnglish (US)
Title of host publication27th International Conference on Intelligent User Interfaces, IUI 2022
PublisherAssociation for Computing Machinery
Pages191-211
Number of pages21
ISBN (Electronic)9781450391443
DOIs
StatePublished - Mar 22 2022
Event27th International Conference on Intelligent User Interfaces, IUI 2022 - Virtual, Online, Finland
Duration: Mar 22 2022Mar 25 2022

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI

Conference

Conference27th International Conference on Intelligent User Interfaces, IUI 2022
Country/TerritoryFinland
CityVirtual, Online
Period3/22/223/25/22

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'How Do People Rank Multiple Mutant Agents?'. Together they form a unique fingerprint.

Cite this