# Application and Evaluation of Large Language Models for Forecasting the Impact of Traffic Incidents

arXiv: https://arxiv.org/abs/2507.04803 · HTML: https://mlsanity.com/paper/2507.04803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 6 of 6)

- [Data Curation Alone Can Stabilize In-context Learning](https://mlsanity.com/paper/2212.10378/) (2022)
- [Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions](https://mlsanity.com/paper/2501.04437/) (2025)
- [Robust Prompt Optimization for Large Language Models Against Distribution Shifts](https://mlsanity.com/paper/2305.13954/) (2023)
- [Enhancing Traffic Incident Management with Large Language Models: A Hybrid Machine Learning Approach for Severity Classification](https://mlsanity.com/paper/2403.13547/) (2024)
- [Arterial incident duration prediction using a bi-level framework of extreme gradient-tree boosting](https://mlsanity.com/paper/1905.12254/) (2019)
- [DG-Trans: Dual-level Graph Transformer for Spatiotemporal Incident Impact Prediction on Traffic Networks](https://mlsanity.com/paper/2303.12238/) (2023)

## Abstract (arXiv)

This study examines the feasibility of applying large language models (LLMs) for forecasting the impact of traffic incidents on the traffic flow. The use of LLMs for this task has several advantages over existing machine learning-based solutions such as not requiring a large training dataset and the ability to utilize free-text incident logs. We propose a fully LLM-based solution that predicts the incident impact using a combination of traffic features and LLM-extracted incident features. A key ingredient of this solution is an effective method of selecting examples for the LLM's in-context learning. We evaluate the performance of three advanced LLMs and two state-of-the-art machine learning models on a real traffic incident dataset. The results show that the best-performing LLM matches the accuracy of the most accurate machine learning model, despite the former not having been trained on this prediction task. The findings indicate that LLMs are a practically viable option for traffic incident impact prediction.