让聊天机器人推荐笔记本更透明，但用户仍难理解推荐理由。
Transparent by Design, Usable in Practice? A Formative Usability Study of a Conversational Product Advisor
- 用限定生成+实时解释+对比功能设计透明推荐
- 用户满意但解释内容反而引发最严重使用问题
- 适合关注人机交互与可解释性设计的研究者
大型语言模型能让对话式产品推荐系统表达流畅却缺乏透明度。若推荐逻辑和证据隐藏在自然语言回复中，会削弱用户的理解、信任与控制能力。一种应对策略是将透明性融入系统设计。我们开展了一项形成性、受控的思考过程访谈研究，评估一个笔记本电脑推荐聊天机器人：该系统采用受限自然语言生成、按需排名解释和比较功能。七名参与者完成三项搜索任务，并报告任务后可用性评分。我们对会话进行编码，识别出严重程度分级的可用性问题。任务中的易用性和满意度较高，但两个发现突出：第一，设计上的透明并未带来理解——多名参与者虽认可解释的价值，但其成为最严重的使用障碍；第二，用户赞赏系统节省的时间，但部分人希望增加直接操作控制。本文贡献了一个按严重性排序的可用性问题清单及面向以人为本的对话式产品推荐系统的设计启示。
原文摘要 · Abstract (English)
Large language models can make conversational product advisors fluent but opaque. If they hide the logic behind a ranking and the evidence for a recommendation inside natural-language replies, they challenge users' ability to understand, trust, and steer the results. One response is to build transparency into the advisor. We report a formative, moderated think-aloud usability study of one such system: a chatbot for laptop search with constrained natural-language generation, an on-demand ranking explanation, and a comparison feature. Seven participants completed three laptop-search tasks and reported post-task usability measures. We coded their sessions into severity-rated usability problems. Ease and satisfaction during the tasks were high, but two findings stand out. First, transparency by design did not guarantee understanding: several participants valued the ranking explanation in principle, yet it caused the most severe problem. Second, participants valued the effort the advisor saved, but some wanted additional direct-manipulation controls. We contribute a severity-prioritized set of usability problems and design implications for human-centered conversational product advisors.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。