Transparent by Design, Usable in Practice? A Formative Usability Study of a Conversational Product Advisor
2.60T1 sourcearXiv cs.HC
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2607.21513.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryFormative think-aloud usability study of a chatbot laptop-search advisor with transparency features including constrained generation, on-demand ranking explanations, and comparison. Seven participants completed three tasks. Ease and satisfaction were high, but the ranking explanation caused the most severe usability problem, and several wanted direct-manipulation controls.
Why it mattersReports a counterintuitive finding that explicit transparency features produced the worst usability problem, with concrete design implications for conversational AI recommenders.
Cited by
No citations on record.
