arXiv：cs.AI· Raquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko, Eunice Son, Shambhavi Verma, Brian O'Leary, Venketesh Subramony, Sylvain Nazef, Jacquelyn Elias, Ron Coddington, Chris Contakes, Michael Riley, Naren Ramakrishnan·· 5 小时前AI 评分31
DataWeave：面向探索性结构化数据分析的人机协作分析系统
DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis
AI 导读
DataWeave 是一个结合对话交互、schema grounding、分析规划与可执行查询生成的系统，用于支持结构化数据的探索性分析。该系统将 LLM 定位为可检查、可纠正、可引导的交互伙伴，而非自主答案引擎，并与专业记者合作分析了美国教育部 IPEDS 数据集。研究还总结了部署经验与迭代改进对 DataWeave 架构和分析工作流的影响。
正文
Authors:Raquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko, Eunice Son, Shambhavi Verma, Brian O'Leary, Venketesh Subramony, Sylvain Nazef, Jacquelyn Elias, Ron Coddington, Chris Contakes, Michael Riley, Naren Ramakrishnan
Abstract:Data journalism, the practice of using data analysis to surface newsworthy stories, depends increasingly on the ability of reporters and investigative journalists to uncover trends, disparities, and accountability narratives. In practice, exploring large structured datasets remains slow and brittle: journalists must navigate hundreds of variables across many datasets over years, understand data coding conventions, and write non-trivial analysis code while hypotheses evolve. Although LLMs are often touted as "ask in English, get SQL/answers," real newsroom workflows expose recurring failures, e.g., schema mismatches and drift, misread domain semantics and units, and silent assumptions. We present DataWeave, a system that addresses these needs by combining conversational interaction, schema grounding, analytical planning, and executable query generation to support exploratory analysis over structured data. Rather than treating LLMs as autonomous answer engines, DataWeave frames them as interactive partners whose outputs can be inspected, corrected, and steered as hypotheses shift. We present a case study with professional journalists using our system to analyze the U.S. Department of Education's Integrated Postsecondary Education Data System (IPEDS), a high-stakes public dataset with substantial domain semantics and frequent schema updates. We also report how deployment experience and iterative refinement shaped the current DataWeave architecture and its analytical workflow. Our findings distill design principles and deployment lessons for trustworthy human-LLM collaboration in structured data analysis.
| Subjects: | Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2610.02679 [cs.AI] |
| (or arXiv:2610.02679v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02679 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Raquib Bin Yousuf [view email]
[v1]
Fri, 2 Oct 2026 02:00:28 UTC (4,030 KB)
来源：arXiv：cs.AI · arxiv.org