发表机构
Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对大语言模型长响应中用户管理不确定性的难题，通过形成性研究得出设计准则，构建U-Lens系统，经实验评估，该系统能提高验证效率、降低工作量、加强各阶段感知支持，重塑了生成式AI的不确定性支持方式。
AI 中文摘要
大语言模型越来越多地用于为知识密集型任务生成长篇答案，但用户难以决定响应的哪些部分值得审查、为何不可靠以及后续该怎么做。先前不确定性通信工作主要聚焦通过置信分数等线索使不确定性可见，对管理长响应中不确定性的整体过程支持不足。通过一项形成性研究，我们考察用户在解释、评估和决策三个阶段如何管理不确定性。基于这些见解，我们得出设计准则并在U-Lens中实例化，它将长响应中的不确定信息组织成上下文检查目标，对其进行优先级排序，并将每个目标与评估上下文和响应选项相连接。在一项有18名参与者的受控受试者内研究中评估U-Lens，结果表明它提高了验证效率和精力分配，降低了感知工作量，并加强了各阶段的感知支持。这项工作将生成式人工智能的不确定性支持从呈现孤立的、以文本为中心的线索重新构建为支持以用户为中心的解释、评估和处理不确定信息的过程。
英文摘要
Uncertainty can appear throughout LLM-generated text (e.g., questionable claims, ambiguous terms). Prior work largely focuses on making such uncertainty visible through cues such as confidence scores, but seeing uncertainty is not the same as managing it. Through a formative study, we examine uncertainty management across interpretation, evaluation, and decision. From these insights, we derive design guidelines for uncertainty target representation, evaluative explanation, response guidance, and interactive presentation. We instantiate them in U-Lens, an uncertainty-management system that organizes uncertain information into contextual inspection targets, prioritizes them, and links each to evaluative context and response options. In an 18-participant within-subjects study comparing U-Lens with a confidence-cue baseline, U-Lens improved verification efficiency and effort allocation, reduced perceived workload, and strengthened support across all three stages. This work reframes uncertainty support for generative AI from text-centered cues to a user-centered process of interpreting, evaluating, and acting on uncertainty.
