XAlgo: a Design Probe of Explaining Algorithms' Internal States via Question-Answering
This addresses the need for non-experts like students or operators to understand algorithm internal states, but it is incremental as it builds on prior explainable AI work with a specific interactive method.
The paper tackles the problem of explaining deterministic algorithms to non-expert users by proposing XAlgo, an interactive question-answering approach, and reports findings from a design probe with 18 participants on question types, response quality, and remaining challenges.
Algorithms often appear as 'black boxes' to non-expert users. While prior work focuses on explainable representations and expert-oriented exploration, we propose and study an interactive approach using question answering to explain deterministic algorithms to non-expert users who need to understand the algorithms' internal states (e.g., students learning algorithms, operators monitoring robots, admins troubleshooting network routing). We construct XAlgo -- a formal model that first classifies the type of question based on a taxonomy and generates an answer based on a set of rules that extract information from representations of an algorithm's internal states, e.g., the pseudocode. A design probe in an algorithm learning scenario with 18 participants (9 for a Wizard-of-Oz XAlgo and 9 as a control group) reports findings and design implications based on what kinds of questions people ask, how well XAlgo responds, and what remain as challenges to bridge users' gulf of understanding algorithms.