# Learning Traffic Crashes as Language: Datasets, Benchmarks, and What-if Causal Analyses

arXiv: https://arxiv.org/abs/2406.10789 · HTML: https://mlsanity.com/paper/2406.10789/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 16 Jun 2024.

## Builds on (most cited first, 7 of 7)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [S3: Social-network Simulation System with Large Language Model-Empowered Agents](https://mlsanity.com/paper/2307.14984/) (2023)
- [Bayesian Structure Learning with Generative Flow Networks](https://mlsanity.com/paper/2202.13903/) (2022)

## Built on by (most cited first, 10 of 10)

- [Safety Guardrails for LLM-Enabled Robots](https://mlsanity.com/paper/2503.07885/) (2025)
- [Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap](https://mlsanity.com/paper/2503.21411/) (2025)
- [Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review](https://mlsanity.com/paper/2506.06301/) (2025)
- [Generative AI for Autonomous Driving: Frontiers and Opportunities](https://mlsanity.com/paper/2505.08854/) (2025)
- [Jailbreaking LLM-Controlled Robots](https://mlsanity.com/paper/2410.13691/) (2024)
- [CrashSage: A Large Language Model-Centered Framework for Contextual and Interpretable Traffic Crash Analysis](https://mlsanity.com/paper/2505.07853/) (2025)
- [Predicting person-level injury severity using crash narratives: A balanced approach with roadway classification and natural language process techniques](https://mlsanity.com/paper/2509.07845/) (2025)
- [An Agentic Workflow for Detecting Personally Identifiable Information in Crash Narratives](https://mlsanity.com/paper/2604.15369/) (2026)
- [TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability Determination](https://mlsanity.com/paper/2606.01737/) (2026)
- [Responsibility Distribution Estimation in Ego-View Accident Videos with Multimodal Large Language Models](https://mlsanity.com/paper/2607.03591/) (2026)

## Abstract (arXiv)

The increasing rate of road accidents worldwide results not only in significant loss of life but also imposes billions financial burdens on societies. Current research in traffic crash frequency modeling and analysis has predominantly approached the problem as classification tasks, focusing mainly on learning-based classification or ensemble learning methods. These approaches often overlook the intricate relationships among the complex infrastructure, environmental, human and contextual factors related to traffic crashes and risky situations. In contrast, we initially propose a large-scale traffic crash language dataset, named CrashEvent, summarizing 19,340 real-world crash reports and incorporating infrastructure data, environmental and traffic textual and visual information in Washington State. Leveraging this rich dataset, we further formulate the crash event feature learning as a novel text reasoning problem and further fine-tune various large language models (LLMs) to predict detailed accident outcomes, such as crash types, severity and number of injuries, based on contextual and environmental factors. The proposed model, CrashLLM, distinguishes itself from existing solutions by leveraging the inherent text reasoning capabilities of LLMs to parse and learn from complex, unstructured data, thereby enabling a more nuanced analysis of contributing factors. Our experiments results shows that our LLM-based approach not only predicts the severity of accidents but also classifies different types of accidents and predicts injury outcomes, all with averaged F1 score boosted from 34.9% to 53.8%. Furthermore, CrashLLM can provide valuable insights for numerous open-world what-if situational-awareness traffic safety analyses with learned reasoning features, which existing models cannot offer. We make our benchmark, datasets, and model public available for further exploration.