InsightChain：面向LLM驱动数据可视化的优化洞察链分析
InsightChain: Optimized Chain-of-Insight Analytics for LLM-driven Data Visualization
浏览论文内容
中文总结 AI 辅助
InsightChain提出四阶段可视化提示流水线及视觉引导优化方法，引入新评估指标，在公共数据集上优于基线，解决了LLM可视化中缺乏迭代分析的问题。
中文摘要 AI 辅助
大型语言模型（LLMs）越来越多地被用于自动化数据可视化，然而现有方法通常将可视化生成视为从用户查询到图形或代码的单步映射，忽略了专家分析师的迭代分析推理过程。我们提出了InsightChain，一个四阶段可视化提示流水线（探索-聚焦-测试-呈现），模拟专家分析工作流，并配合VG-COPRO，一种视觉引导的自动提示优化（APO）方法，用于联合优化这种多阶段、可执行的流水线。为了解决复杂数据可视化的评估缺口，我们引入了洞察进展度量（IPM），一个结合四个基于文本的维度和一个基于视觉的维度的评估标准。我们通过一个100链的人类试点和一个覆盖所有十个领域的扩展300链基于代理的评估来评估IPM。在公共数据集上的实验表明，InsightChain始终优于竞争的提示基线。现有的APO方法未能在此多阶段任务上产生一致的收益，而VG-COPRO在领域内和跨领域设置中均提升了性能。
英文摘要
Large language models (LLMs) are increasingly used for automated data visualization, yet existing approaches often frame visualization generation as a single-step mapping from user query to figure or code, overlooking the iterative analytical reasoning process of expert analysts. We present InsightChain, a four-stage visualization prompting pipeline (Explore--Focus--Test--Present) that emulates expert analytical workflows, together with VG-COPRO, a vision-guided automatic prompt optimization (APO) method adapted to jointly optimize such multi-stage, executable pipelines. To address the evaluation gap for complex data visualization, we introduce the Insight Progression Metric (IPM), a rubric combining four text-based dimensions with a vision-based dimension. We assess IPM through a 100-chain human pilot and an expanded 300-chain agent-based evaluation spanning all ten domains. Experiments on public datasets show that InsightChain consistently outperforms competing prompting baselines. Existing APO methods fail to yield consistent gains on this multi-stage task, whereas VG-COPRO improves performance in both in-domain and cross-domain settings.
发表机构
- Huawei Technologies Co., Ltd.（华为技术有限公司）
机构由 AI 辅助整理，请以论文原文为准。
