实时可视化用户与AI互动中的信任变化，助力设计更可信的对话系统。
VizTrust: A Visual Analytics Tool for Capturing User Trust Dynamics in Human-AI Communication
- 基于多智能体协作，实时追踪用户对AI的信任动态
- 通过四大信任维度（能力、诚信、善意、可预测性）量化信任演变
- 适合人机交互、AI可信度研究者使用
信任在用户与人工智能系统协作中起关键作用，但其复杂且动态的特性使得测量困难。传统问卷方法仅能提供长对话后的整体信任水平，无法捕捉互动过程中的信任演化。为此，我们提出VizTrust，一个基于多智能体协作系统的实时可视化分析工具，用于捕捉和分析人-代理交互中的信任动态。该工具依托公认的人机信任量表——能力、诚信、善意与可预测性，使利益相关方能够实时观察信任形成过程，识别信任发展的模式，并定位影响信任的具体交互要素。通过仪表盘界面，VizTrust为人类-代理信任的形成与演化提供实时可操作洞察，支持设计能响应用户信任信号的自适应对话代理。
原文摘要 · Abstract (English)
Trust plays a fundamental role in shaping the willingness of users to engage and collaborate with artificial intelligence (AI) systems. Yet, measuring user trust remains challenging due to its complex and dynamic nature. While traditional survey methods provide trust levels for long conversations, they fail to capture its dynamic evolution during ongoing interactions. Here, we present VizTrust, which addresses this challenge by introducing a real-time visual analytics tool that leverages a multi-agent collaboration system to capture and analyze user trust dynamics in human-agent communication. Built on established human-computer trust scales-competence, integrity, benevolence, and predictability-, VizTrust enables stakeholders to observe trust formation as it happens, identify patterns in trust development, and pinpoint specific interaction elements that influence trust. Our tool offers actionable insights into human-agent trust formation and evolution in real time through a dashboard, supporting the design of adaptive conversational agents that responds effectively to user trust signals.
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。