2026-10-14T13:58:11Z https://api.figshare.com/v2/oai

oai:figshare.com:article/34025198 2026-09-29T16:43:07Z category_15 category_272 category_45 category_734 category_106 category_122 portal_87 item_type_6 month_year_09_2026

Explanation type and appropriate reliance in AI-assisted patent evaluation: an exploratory study across user domain familiarity Jane Lee (7063) Jaehoo Bae (25137959) Eunseo Ryu (25137962) Leehee Kim (25137965) Dain Kim (6946190) Sungjoo Lee (1527352) Myung Hwan Yun (3987329) Neuroscience Environmental Sciences not elsewhere classified Sociology Biological Sciences not elsewhere classified Science Policy Mental Health Explainable AI trust calibration appropriate reliance human-AI collaboration decision support <p>Explainable AI (XAI) aims to foster appropriate reliance, but its effectiveness may depend on users’ domain familiarity. We conducted an exploratory study of a simplified patent-evaluation task representative of consequential decision-support settings, comparing a feature-based (SHAP) and an example-based (two-case contrastive) explanation display with 9 domain-familiar and 24 lay participants. In both groups, the example-based condition showed a significant within-condition improvement of final over initial decisions on the same items, with no detected difference in gains between conditions. Among domain-familiar participants, switching to correct AI advice given disagreement was substantially lower under the feature-based than the example-based display, despite their stated preference for the feature-based format; among lay participants, no differences in switching to correct AI advice were detected once disagreement opportunities were considered. These findings caution against preference-driven XAI design: the display domain-familiar users preferred was the one under which they most often discarded correct AI advice.</p> <p>This exploratory study examined how explanation type relates to reliance on AI advice. In a patent-based technology evaluation task, 33 participants used feature-based and example-based explanation displays. The example-based condition showed a significant within-condition improvement over the same-item baseline, with no detected difference in gains between conditions; domain-familiar users switched to correct AI advice far less often under the feature-based display despite preferring it, cautioning against preference-driven design.</p> 2026-09-29T16:43:07Z Text Journal contribution 10.6084/m9.figshare.34025198.v1 https://figshare.com/articles/journal_contribution/Explanation_type_and_appropriate_reliance_in_AI-assisted_patent_evaluation_an_exploratory_study_across_user_domain_familiarity/34025198 CC BY 4.0