AI 中文总结
本研究通过评估GPT-5等LLMs在单/多智能体模式下的表现，探究其在AI辅助可视化中检测修复数据问题的能力，发现其在单字段问题上表现良好但在时间等问题上存在不足，并提出智能体可视化系统的设计启示。
AI 中文摘要
AI正不断降低数据分析的门槛并生成可视化脚本，但AI辅助可视化的一个关键障碍是，某些数据问题会生成看似合理却歪曲底层数据的可视化结果。这些“可视化缺陷”难以捉摸且难以修复，尤其是对于非专业人士而言，他们可能不知道哪些数据问题会引发缺陷，也不知道如何指导AI系统解决问题。本文呈现了一项初步实证研究的结果，该研究探究商业大型语言模型（LLMs）如何识别和修复引发缺陷的数据问题。我们使用注入了5个数据问题的911紧急呼叫数据集的精选子集，在三阶段提示协议（包括零样本、引导式问题识别和引导式问题修复）下评估了GPT-5、GPT-4o、GPT-4和Claude Sonnet 4.6。我们在两种条件下执行该协议：单智能体模式和分离数据问题检测、审核、修复规划、数据修复及修复质量保障的多智能体编排模式。我们观察到，在两种条件下，LLMs都能识别并修复单字段问题（如缺失值），但在识别和修复时间、地理及语义问题上存在困难。基于这些观察，我们讨论了智能体可视化系统的设计启示，包括明确表示数据假设、针对模糊决策进行选择性人工干预以及基于证据的修复。
英文摘要
AI is increasingly lowering the barrier to data analysis and creating visualization scripts. However, a key obstacle in AI-assisted visualization is that certain data issues can lead to visualizations that are plausible, but misrepresent the underlying data. These \textit{visualization defects} are elusive and difficult to fix, particularly for non-experts who may not know what data issues cause them or how to guide AI systems to resolve them. We present findings of a preliminary empirical investigation of how commercial LLMs identify and repair defect-inducing data issues. Using a curated subset of the 911 emergency-call dataset with five injected data issues, we evaluated GPT-5, GPT-4o, GPT-4, and Claude Sonnet 4.6 under a three-stage prompting protocol, including zero-shot, guided issue-identification, and guided issue-repair. We executed this protocol under two conditions: single-agent and a multi-agent orchestration that separates data issue detection, review, repair planning, data repair, and repair quality assurance. We observed that across both conditions, LLMs identified and repaired single-field issues (e.g., missing values) but struggled to identify and repair temporal, geographic, and semantic issues. Based on these observations, we discuss design implications for agentic visualization systems, including explicit representation of data assumptions, selective human intervention for ambiguous decisions, and evidence-based repair.
