# Towards Reliable and Interpretable Traffic Crash Pattern Prediction and Safety Interventions Using Customized Large Language Models

arXiv: https://arxiv.org/abs/2505.12545 · HTML: https://mlsanity.com/paper/2505.12545/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 54 references that are in the map.
- First posted on arXiv 18 May 2025.

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Algorithms to estimate Shapley value feature attributions](https://mlsanity.com/paper/2207.07605/) (2022)
- [From Shapley Values to Generalized Additive Models and back](https://mlsanity.com/paper/2209.04012/) (2022)
- [TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation](https://mlsanity.com/paper/2407.10114/) (2024)
- [Explaining a Series of Models by Propagating Shapley Values](https://mlsanity.com/paper/2105.00108/) (2021)
- [Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference](https://mlsanity.com/paper/2408.04652/) (2024)
- [Advancing Real-time Pandemic Forecasting Using Large Language Models: A COVID-19 Case Study](https://mlsanity.com/paper/2404.06962/) (2024)

## Built on by (most cited first, 1 of 1)

- [Benchmarking Frontier Large Language Models Against Official Crash Database Coding Using Police Crash Narratives](https://mlsanity.com/paper/2607.29064/) (2026)

## Abstract (arXiv)

Predicting crash events is crucial for understanding crash distributions and their contributing factors, thereby enabling the design of proactive traffic safety policy interventions. However, existing methods struggle to interpret the complex interplay among various sources of traffic crash data, including numeric characteristics, textual reports, crash imagery, environmental conditions, and driver behavior records. As a result, they often fail to capture the rich semantic information and intricate interrelationships embedded in these diverse data sources, limiting their ability to identify critical crash risk factors. In this research, we propose TrafficSafe, a framework that adapts LLMs to reframe crash prediction and feature attribution as text-based reasoning. A multi-modal crash dataset including 58,903 real-world reports together with belonged infrastructure, environmental, driver, and vehicle information is collected and textualized into TrafficSafe Event Dataset. By customizing and fine-tuning LLMs on this dataset, the TrafficSafe LLM achieves a 42% average improvement in F1-score over baselines. To interpret these predictions and uncover contributing factors, we introduce TrafficSafe Attribution, a sentence-level feature attribution framework enabling conditional risk analysis. Findings show that alcohol-impaired driving is the leading factor in severe crashes, with aggressive and impairment-related behaviors having nearly twice the contribution for severe crashes compared to other driver behaviors. Furthermore, TrafficSafe Attribution highlights pivotal features during model training, guiding strategic crash data collection for iterative performance improvements. The proposed TrafficSafe offers a transformative leap in traffic safety research, providing a blueprint for translating advanced AI technologies into responsible, actionable, and life-saving outcomes.