Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries
Quick Answer
This paper introduces a schema-grounded natural language interface for transportation safety analysis, leveraging a large language model to enhance access to safety data while ensuring reproducibility and governance.
Quick Take
This paper introduces a schema-grounded natural language interface for transportation safety analysis, leveraging a large language model to enhance access to safety data while ensuring reproducibility and governance. The framework successfully integrates crash records and geospatial data, correcting 29% of user query errors, thereby bridging the gap between technical tools and community stakeholders.
Key Points
- Generative AI narrows the gap in transportation safety data access for local agencies.
- User queries are transformed into structured semantic frames for accurate execution.
- The framework uses a PostGIS database to manage spatial operations effectively.
- 29% of user query errors were corrected by the validation layer during evaluation.
- The approach enhances trust in AI for public-sector planning and safety analysis.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Transportation safety analysis requires integrating crash records, roadway attributes, and geospatial data through GIS-based workflows, but access remains uneven across agencies and community stakeholders. Technical prerequisites create a gap between analytical tools central to safety planning and the practitioners able to use them. Local agencies, school committees, and residents may have safety concerns but limited capacity to retrieve, filter, map, and analyze relevant data. Generative AI offers a way to narrow this divide, but its public-sector use raises questions about reliability, reproducibility, and governance. This paper presents a schema-grounded natural language interface for transportation safety analysis, using a large language model (LLM) to interpret user intent while preserving deterministic, reviewable execution against an authoritative database. User queries are translated into structured semantic frames, validated by a rule-based layer, compiled into a typed directed acyclic graph of spatial operations, and executed against a PostGIS database. This bounded design separates language interpretation from deterministic execution, keeping results reproducible and schema-grounded while removing access barriers. The framework is evaluated using a statewide Massachusetts transportation safety database integrating crash records, roadway attributes, and geospatial layers including schools, bus stops, crosswalks, and municipal boundaries. All queries executed successfully; the validation layer corrects errors in 29% of evaluation queries, reflecting the gap between flexible natural language and strict schema-grounded requirements. The results suggest that combining natural language accessibility with deterministic execution is a practical direction for broadening access to transportation safety data, with implications for trustworthy AI in public-sector planning.
| Comments: | 30 pages, 5 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2605.21712 [cs.CL] |
| (or arXiv:2605.21712v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.21712 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mahdi Azhdari [view email]
[v1]
Wed, 20 May 2026 20:14:55 UTC (1,289 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Quantifying Prior Dominance in Systems
The study introduces the Normalized Context Utilization (NCU) metric to evaluate Retrieval-Augmented Generation (RAG) systems, revealing that Small Language Models (SLMs) outperform larger models in factual extraction. The findings indicate that traditional scaling laws yield diminishing returns, with a commercial API frequently failing against adversarial evidence due to systemic confidence collapse.