# Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference

arXiv: https://arxiv.org/abs/2408.04652 · HTML: https://mlsanity.com/paper/2408.04652/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning.
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 4 Aug 2024.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)

## Builds on (most cited first, 5 of 5)

- [Multimodal Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2302.00923/) (2023)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning](https://mlsanity.com/paper/2310.00492/) (2023)
- [Meta-learning for Few-shot Natural Language Processing: A Survey](https://mlsanity.com/paper/2007.09604/) (2020)
- [Aligning Large Language Models with Human: A Survey](https://mlsanity.com/paper/2307.12966/) (2023)

## Built on by (most cited first, 14 of 14)

- [Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review](https://mlsanity.com/paper/2506.06301/) (2025)
- [CrashSage: A Large Language Model-Centered Framework for Contextual and Interpretable Traffic Crash Analysis](https://mlsanity.com/paper/2505.07853/) (2025)
- [How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation](https://mlsanity.com/paper/2510.21148/) (2025)
- [Urban Computing in the Era of Large Language Models](https://mlsanity.com/paper/2504.02009/) (2025)
- [Towards Reliable and Interpretable Traffic Crash Pattern Prediction and Safety Interventions Using Customized Large Language Models](https://mlsanity.com/paper/2505.12545/) (2025)
- [MPCAR: Multi-Perspective Contextual Augmentation for Enhanced Visual Reasoning in Large Vision-Language Models](https://mlsanity.com/paper/2508.12400/) (2025)
- [Domain-Adapted Pre-trained Language Models for Implicit Information Extraction in Crash Narratives](https://mlsanity.com/paper/2510.09434/) (2025)
- [X-Blocks: Linguistic Building Blocks of Natural Language Explanations for Automated Vehicles](https://mlsanity.com/paper/2602.13248/) (2026)
- [TrafficRAG: A Multimodal RAG Framework for Traffic Accident Liability Determination](https://mlsanity.com/paper/2606.01737/) (2026)
- [Design and Application of Multimodal Large Language Model Based System for End to End Automation of Accident Dataset Generation](https://mlsanity.com/paper/2505.00015/) (2025)
- [Automating Crash Diagram Generation Using Vision-Language Models: A Case Study on Multi-Lane Roundabouts](https://mlsanity.com/paper/2604.15332/) (2026)
- [Earth Science Foundation Models: From Perception to Reasoning and Discovery](https://mlsanity.com/paper/2605.12542/) (2026)
- [Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support](https://mlsanity.com/paper/2606.00991/) (2026)
- [Responsibility Distribution Estimation in Ego-View Accident Videos with Multimodal Large Language Models](https://mlsanity.com/paper/2607.03591/) (2026)

## Abstract (arXiv)

Harnessing the power of Large Language Models (LLMs), this study explores the use of three state-of-the-art LLMs, specifically GPT-3.5-turbo, LLaMA3-8B, and LLaMA3-70B, for crash severity inference, framing it as a classification task. We generate textual narratives from original traffic crash tabular data using a pre-built template infused with domain knowledge. Additionally, we incorporated Chain-of-Thought (CoT) reasoning to guide the LLMs in analyzing the crash causes and then inferring the severity. This study also examine the impact of prompt engineering specifically designed for crash severity inference. The LLMs were tasked with crash severity inference to: (1) evaluate the models' capabilities in crash severity analysis, (2) assess the effectiveness of CoT and domain-informed prompt engineering, and (3) examine the reasoning abilities with the CoT framework. Our results showed that LLaMA3-70B consistently outperformed the other models, particularly in zero-shot settings. The CoT and Prompt Engineering techniques significantly enhanced performance, improving logical reasoning and addressing alignment issues. Notably, the CoT offers valuable insights into LLMs' reasoning processes, unleashing their capacity to consider diverse factors such as environmental conditions, driver behavior, and vehicle characteristics in severity analysis and inference.