Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries

• URL: http://arxiv.org/abs/2605.21712v1
• Date: Wed, 20 May 2026 20:14:55 GMT
• Title: Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries
• Abstract summary: This paper presents a schema-grounded natural language interface for transportation safety analysis using a large language model (LLM)<n>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.<n>Results suggest that combining natural language accessibility with deterministic execution is a practical direction for broadening access to transportation safety data.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy Mitigation [48.55515767840701]
  "AI slop" is artifacts, hallucinated vulnerabilities, plausible but incorrect patches, and semantically repackaged bug reports.<n>This paper surveys the empirical evidence, identifies a unifying mechanism, and traces a path toward trustworthy triage.
  arXiv  Detail & Related papers  (2026-08-26T11:48:38Z)
• Risk-Aware LLM Agents for Geospatial Data Retrieval: Design and Preliminary Adversarial Evaluation [13.556629148264994]
  The system converts user intent into structured API calls, enabling efficient access to satellite imagery and environmental datasets.<n>The modular framework is portable across platforms through API schema substitution and supports applications in environmental monitoring, disaster response, and climate analysis.
  arXiv  Detail & Related papers  (2026-06-13T03:15:53Z)
• Generation of Human Comprehensible Access Control Policies from Audit Logs [2.839132202833286]
  We develop a framework that generates human understandable natural language access control policies from logs.<n>Named LANTERN (LLM-based ABAC Natural Translation and Explanation for Rule Navigation), we have instantiated the framework as a publicly accessible web based application for our results.
  arXiv  Detail & Related papers  (2026-03-15T12:21:27Z)
• Semantic Risk Scoring of Aggregated Metrics: An AI-Driven Approach for Healthcare Data Governance [0.0]
  Large healthcare institutions typically operate multiple business intelligence (BI) teams.<n>Due to HIPAA, FERPA, and IRB restrictions, these teams face challenges in sharing patient-level data needed for analytics.<n>A metric aggregation table is proposed, which is a precomputed, privacy-compliant summary.
  arXiv  Detail & Related papers  (2026-03-09T03:36:11Z)
• RedacBench: Can AI Erase Your Secrets? [48.280759014096354]
  We introduce RedacBench, a benchmark for evaluating policy-conditioned redaction across domains and strategies.<n>RedacBench measures a model's ability to selectively remove policy-violating information while preserving the original semantics.<n>We quantify performance using 8,053 annotated propositions that capture all inferable information in each text.
  arXiv  Detail & Related papers  (2026-03-02T06:29:49Z)
• CrossTraffic: An Open-Source Framework for Reproducible and Executable Transportation Analysis and Knowledge Management [18.821780833520116]
  CrossTraffic is an open-source framework that treats transportation methodologies and regulatory knowledge as continuously deployable and verifiable software infrastructure.<n>CrossTraffic provides an executable computational core for transportation analysis with cross-platform access through standardized interfaces.
  arXiv  Detail & Related papers  (2026-02-08T22:30:27Z)
• X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles [14.815119135668247]
  Natural language explanations play a critical role in establishing trust and acceptance of automated vehicles (AVs)<n>This paper introduces X-Blocks, a hierarchical analytical framework that identifies the linguistic building blocks of natural language explanations for AVs at three levels: context, syntax, and lexicon.<n> RACE achieves 91.45 percent accuracy and a Cohens kappa of 0.91 against cases with human annotator agreement, indicating near-human reliability for context classification.
  arXiv  Detail & Related papers  (2026-02-02T07:18:25Z)
• ALIGN: A Vision-Language Framework for High-Accuracy Accident Location Inference through Geo-Spatial Neural Reasoning [0.0]
  Most low- and middle-income countries face a critical shortage of accurate, location-specific crash data.<n>Existing text-based geocoding tools perform poorly in multilingual and unstructured news environments.<n>This study introduces ALIGN, a vision-language framework that emulates human spatial reasoning to infer accident coordinates.
  arXiv  Detail & Related papers  (2025-11-09T10:44:26Z)
• Cross-Dataset Semantic Segmentation Performance Analysis: Unifying NIST Point Cloud City Datasets for 3D Deep Learning [49.1574468325115]
  This study analyzes semantic segmentation performance across heterogeneously labeled point-cloud datasets relevant to public safety applications.<n>Key identified challenges include insufficient labeled data, difficulties in unifying class labels across datasets, and the need for standardization.
  arXiv  Detail & Related papers  (2025-08-01T17:59:02Z)
• Foundation Models for Logistics: Toward Certifiable, Conversational Planning Interfaces [59.80143393787701]
  Large language models (LLMs) can handle uncertainty and promise to accelerate replanning while lowering the barrier to entry.<n>We introduce a neurosymbolic framework that pairs the accessibility of natural-language dialogue with verifiable guarantees on goal interpretation.<n>A lightweight model, fine-tuned on just 100 uncertainty-filtered examples, surpasses the zero-shot performance of GPT-4.1 while cutting inference latency by nearly 50%.
  arXiv  Detail & Related papers  (2025-07-15T14:24:01Z)
• Knowledge Graph Completion with Relation-Aware Anchor Enhancement [50.50944396454757]
  We propose a relation-aware anchor enhanced knowledge graph completion method (RAA-KGC)<n>We first generate anchor entities within the relation-aware neighborhood of the head entity.<n>Then, by pulling the query embedding towards the neighborhoods of the anchors, it is tuned to be more discriminative for target entity matching.
  arXiv  Detail & Related papers  (2025-04-08T15:22:08Z)
• How Context Affects Language Models' Factual Predictions [134.29166998377187]
  We integrate information from a retrieval system with a pre-trained language model in a purely unsupervised way. We report that augmenting pre-trained language models in this way dramatically improves performance and that the resulting system, despite being unsupervised, is competitive with a supervised machine reading baseline.
  arXiv  Detail & Related papers  (2020-05-10T09:28:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.