Human-centered explanation does not fit all: The interplay of sociotechnical, cognitive, and individual factors in the effect AI explanations in algorithmic decision-making
This work addresses the problem of designing effective AI explanations for diverse users in decision-making contexts, offering incremental insights into human-centered XAI.
The study investigated how different AI explanation strategies affect user preferences and understanding in algorithmic decision-making, finding that contrastive explanations are not universally best and that effectiveness depends on individual and contextual factors.
Recent XAI studies have investigated what constitutes a \textit{good} explanation in AI-assisted decision-making. Despite the widely accepted human-friendly properties of explanations, such as contrastive and selective, existing studies have yielded inconsistent findings. To address these gaps, our study focuses on the cognitive dimensions of explanation evaluation, by evaluating six explanations with different contrastive strategies and information selectivity and scrutinizing factors behind their valuation process. Our analysis results find that contrastive explanations are not the most preferable or understandable in general; Rather, different contrastive and selective explanations were appreciated to a different extent based on who they are, when, how, and what to explain -- with different level of cognitive load and engagement and sociotechnical contexts. Given these findings, we call for a nuanced view of explanation strategies, with implications for designing AI interfaces to accommodate individual and contextual differences in AI-assisted decision-making.