arXiv cs.CL· Jingwen Zhu, Keshu Wu, Steven T. Parker, Bin Ran, David A. Noyce·· 14 小时前AI 评分31
CrashDB-QA：面向自然语言事故数据分析的 schema 接地智能体工作流
From Questions to Queries to Insights: A Schema-Grounded Agentic Workflow for Natural-Language Crash Data Analysis
AI 导读
研究提出 CrashDB-QA，一个完全本地部署、以 schema 为接地的智能体工作流，可将自然语言问题转为只读 SQL 并解释结果，在 440 万条 Wisconsin 事故记录快照和 300 题新基准上测试了 9 个本地开源模型。
正文 · 原文
Abstract:Transportation agencies maintain extensive crash databases to identify safety priorities, evaluate countermeasures, and guide resource allocation. Making these data accessible to practitioners requires flexible ways to translate analytical questions into reliable results. Existing dashboards support predefined analyses, while additional requests often depend on specialists who understand database queries, coded fields, and agency conventions. This study presents CrashDB-QA, a fully local, schema-grounded agentic workflow that enables natural-language analysis of crash databases. Specialized components interpret questions, generate and validate read-only SQL, execute queries, and explain the results. A shared knowledge base grounds query construction in the agency's data dictionary and safety-analysis conventions, while recorded intermediate outputs support inspection and auditing. An optional extension, CrashDB-QA+, checks the alignment among the question, query, and execution result and supplies evidence for iterative repair. We evaluate the workflow on a frozen snapshot of 4.4 million Wisconsin crash records using a new benchmark of 300 questions across ten analytical categories and nine local open-weight models. Domain grounding substantially improves query accuracy, and a code-specialized 7B model provides the best accuracy-latency balance among the tested models. Compositional analyses remain more difficult than routine retrieval, particularly comparisons between groups or periods. Verification improves performance when the Judge uses authoritative field definitions and the Refiner receives execution evidence, whereas additional checking alone offers no consistent benefit. These findings demonstrate the potential of locally deployed, domain-grounded workflows to broaden access to crash analysis and identify the reasoning and verification capabilities needed for reliable use.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.35054 [cs.CL] |
| (or arXiv:2610.35054v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35054 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Keshu Wu [view email]
[v1]
Mon, 26 Oct 2026 09:01:57 UTC (794 KB)
来源：arXiv cs.CL · arxiv.org