arXiv cs.AI· Junran Yang, Shruti Badrish, Teanna Barrett, Leilani Battle·· 9 天前AI 评分24
DAG-EDA：用意图图导航探索性数据分析的推理空间
Intent Graph: Navigating the Analytical Reasoning Space for Exploratory Data Analysis
AI 导读
研究者提出 DAG-EDA 系统，让分析师与 LLM 通过两个关联结构共同导航可能的分析空间：受分析意图语法约束的意图图将模糊的自然语言问题逐步分解为具体分析任务，并保留备选框架供分析师分支、回溯和比较；多层知识图谱则外化 LLM 的领域知识，把领域概念与可测量这些概念的数据集变量关联起来。两个图仅由数据集和分析师的问题构建，最终分析以交互式仪表盘呈现，论文还给出了使用场景与用户研究设计。
正文 · 原文
Abstract:Exploratory data analysis (EDA) is rarely open-ended in practice: analysts work from high-level domain questions toward the concrete analyses that can answer them, prioritizing directions with domain knowledge and prior hypotheses. Large language models (LLMs) can supply such knowledge, but their responses are unstructured, leaving analysts no way to see what has been explored, what is missing, or why one direction was chosen over another. We present DAG-EDA, a system that lets analysts and an LLM co-navigate the space of possible analyses through two linked structures. An intent graph, governed by a grammar of analytical intent, decomposes an ambiguous natural-language question into progressively concrete analysis tasks, keeping alternative framings open and letting analysts branch, backtrack, and compare paths. A multi-layered knowledge graph externalizes the LLM's domain knowledge, linking domain concepts to the dataset variables that can measure them, so analysts can inspect and contest how their question is grounded in the data. Both graphs are constructed from only the dataset and the analyst's question, and the analyses the analyst reaches are rendered as interactive dashboards. We illustrate the system through a usage scenario and describe a user study design for examining whether the system scaffold analysts' reasoning and navigation.
| Subjects: | Human-Computer Interaction (cs.HC); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11025 [cs.HC] |
| (or arXiv:2610.11025v1 [cs.HC] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11025 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junran Yang [view email]
[v1]
Thu, 8 Oct 2026 00:19:01 UTC (2,267 KB)
来源：arXiv cs.AI · arxiv.org