Conversational AI product advisor study reveals transparency challenges

A recent usability study explored the effectiveness of a conversational product advisor designed with transparency in mind. While participants generally found the chatbot helpful for tasks like laptop search, the built-in ranking explanation, intended to foster trust, actually caused the most severe usability issues. Participants appreciated the time saved by the advisor but also expressed a desire for more direct manipulation controls. AI

IMPACT This study highlights the challenges in designing transparent and trustworthy conversational AI for product recommendations, suggesting a need for better integration of direct manipulation controls.

RANK_REASON The cluster contains an academic paper detailing a usability study of a conversational AI product. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.IR (Information Retrieval) →

• arXiv
• chatbot
• Connected Papers
• Conversational product advisor
• Hugging Face
• human–computer interaction
• large-language models
• Litmaps
• scite Smart Citations
• usability study

• paper
• product
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →