Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.13002 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915555545448448 |
|---|---|
| author | Chen, Boyou Xu, Gerui Wang, Zifei Guo, Huizhong Ahmed, Ananna Sun, Zhaonan Hu, Zhen Zhang, Kaihan Bao, Shan |
| author_facet | Chen, Boyou Xu, Gerui Wang, Zifei Guo, Huizhong Ahmed, Ananna Sun, Zhaonan Hu, Zhen Zhang, Kaihan Bao, Shan |
| contents | Vehicle crashes involve complex interactions between road users, split-second decisions, and challenging environmental conditions. Among these, two-vehicle crashes are the most prevalent, accounting for approximately 70% of roadway crashes and posing a significant challenge to traffic safety. Identifying Driver Hazardous Action (DHA) is essential for understanding crash causation, yet the reliability of DHA data in large-scale databases is limited by inconsistent and labor-intensive manual coding practices. Here, we present an innovative framework that leverages a fine-tuned large language model to automatically infer DHAs from textual crash narratives, thereby improving the validity and interpretability of DHA classifications. Using five years of two-vehicle crash data from MTCF, we fine-tuned the Llama 3.2 1B model on detailed crash narratives and benchmarked its performance against conventional machine learning classifiers, including Random Forest, XGBoost, CatBoost, and a neural network. The fine-tuned LLM achieved an overall accuracy of 80%, surpassing all baseline models and demonstrating pronounced improvements in scenarios with imbalanced data. To increase interpretability, we developed a probabilistic reasoning approach, analyzing model output shifts across original test sets and three targeted counterfactual scenarios: variations in driver distraction and age. Our analysis revealed that introducing distraction for one driver substantially increased the likelihood of "General Unsafe Driving"; distraction for both drivers maximized the probability of "Both Drivers Took Hazardous Actions"; and assigning a teen driver markedly elevated the probability of "Speed and Stopping Violations." Our framework and analytical methods provide a robust and interpretable solution for large-scale automated DHA detection, offering new opportunities for traffic safety analysis and intervention. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_13002 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Narratives to Probabilistic Reasoning: Predicting and Interpreting Drivers' Hazardous Actions in Crashes Using Large Language Model Chen, Boyou Xu, Gerui Wang, Zifei Guo, Huizhong Ahmed, Ananna Sun, Zhaonan Hu, Zhen Zhang, Kaihan Bao, Shan Artificial Intelligence Machine Learning Vehicle crashes involve complex interactions between road users, split-second decisions, and challenging environmental conditions. Among these, two-vehicle crashes are the most prevalent, accounting for approximately 70% of roadway crashes and posing a significant challenge to traffic safety. Identifying Driver Hazardous Action (DHA) is essential for understanding crash causation, yet the reliability of DHA data in large-scale databases is limited by inconsistent and labor-intensive manual coding practices. Here, we present an innovative framework that leverages a fine-tuned large language model to automatically infer DHAs from textual crash narratives, thereby improving the validity and interpretability of DHA classifications. Using five years of two-vehicle crash data from MTCF, we fine-tuned the Llama 3.2 1B model on detailed crash narratives and benchmarked its performance against conventional machine learning classifiers, including Random Forest, XGBoost, CatBoost, and a neural network. The fine-tuned LLM achieved an overall accuracy of 80%, surpassing all baseline models and demonstrating pronounced improvements in scenarios with imbalanced data. To increase interpretability, we developed a probabilistic reasoning approach, analyzing model output shifts across original test sets and three targeted counterfactual scenarios: variations in driver distraction and age. Our analysis revealed that introducing distraction for one driver substantially increased the likelihood of "General Unsafe Driving"; distraction for both drivers maximized the probability of "Both Drivers Took Hazardous Actions"; and assigning a teen driver markedly elevated the probability of "Speed and Stopping Violations." Our framework and analytical methods provide a robust and interpretable solution for large-scale automated DHA detection, offering new opportunities for traffic safety analysis and intervention. |
| title | From Narratives to Probabilistic Reasoning: Predicting and Interpreting Drivers' Hazardous Actions in Crashes Using Large Language Model |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2510.13002 |