# CrashSage: A Large Language Model-Centered Framework for Contextual and Interpretable Traffic Crash Analysis

arXiv: https://arxiv.org/abs/2505.07853 · HTML: https://mlsanity.com/paper/2505.07853/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 110 references that are in the map.
- First posted on arXiv 8 May 2025.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [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)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023)
- [Is Attention Interpretable?](https://mlsanity.com/paper/1906.03731/) (2019)
- [GPT-Driver: Learning to Drive with GPT](https://mlsanity.com/paper/2310.01415/) (2023)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation](https://mlsanity.com/paper/2403.06845/) (2024)
- [Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions](https://mlsanity.com/paper/2005.06676/) (2020)
- [Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles](https://mlsanity.com/paper/2309.10228/) (2023)
- [Spatial-Temporal Large Language Model for Traffic Prediction](https://mlsanity.com/paper/2401.10134/) (2024)
- [LLMLight: Large Language Models as Traffic Signal Control Agents](https://mlsanity.com/paper/2312.16044/) (2023)
- [GeoLLM: Extracting Geospatial Knowledge from Large Language Models](https://mlsanity.com/paper/2310.06213/) (2023)
- [From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning](https://mlsanity.com/paper/2310.00492/) (2023)
- [Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era](https://mlsanity.com/paper/2403.08946/) (2024)
- [ChatSUMO: Large Language Model for Automating Traffic Scenario Generation in Simulation of Urban MObility](https://mlsanity.com/paper/2409.09040/) (2024)
- [ChatGraph: Interpretable Text Classification by Converting ChatGPT Knowledge to Graphs](https://mlsanity.com/paper/2305.03513/) (2023)
- [Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmap](https://mlsanity.com/paper/2503.21411/) (2025)
- [MKRAG: Medical Knowledge Retrieval Augmented Generation for Medical Question Answering](https://mlsanity.com/paper/2309.16035/) (2023)
- [TPLLM: A Traffic Prediction Framework Based on Pretrained Large Language Models](https://mlsanity.com/paper/2403.02221/) (2024)
- [Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions](https://mlsanity.com/paper/2501.04437/) (2025)
- [When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis](https://mlsanity.com/paper/2501.10604/) (2025)

## Built on by (most cited first, 6 of 6)

- [Calibrated Decisions at Scale: Converting Police Crash Narratives into Probabilistic Crash Variables with a System One Model (Jev)](https://mlsanity.com/paper/2609.24052/) (2026)
- [STER-VLM: Spatio-Temporal With Enhanced Reference Vision-Language Models](https://mlsanity.com/paper/2508.13470/) (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)
- [EvolveSignal: A Large Language Model Powered Coding Agent for Discovering Traffic Signal Control Strategies](https://mlsanity.com/paper/2509.03335/) (2025)
- [Automating Crash Diagram Generation Using Vision-Language Models: A Case Study on Multi-Lane Roundabouts](https://mlsanity.com/paper/2604.15332/) (2026)
- [Responsibility Distribution Estimation in Ego-View Accident Videos with Multimodal Large Language Models](https://mlsanity.com/paper/2607.03591/) (2026)

## Abstract (arXiv)

Road crashes claim over 1.3 million lives annually worldwide and incur global economic losses exceeding 1.8 trillion. Such profound societal and financial impacts underscore the urgent need for road safety research that uncovers crash mechanisms and delivers actionable insights. Conventional statistical models and tree ensemble approaches typically rely on structured crash data, overlooking contextual nuances and struggling to capture complex relationships and underlying semantics. Moreover, these approaches tend to incur significant information loss, particularly in narrative elements related to multi-vehicle interactions, crash progression, and rare event characteristics. This study presents CrashSage, a novel Large Language Model (LLM)-centered framework designed to advance crash analysis and modeling through four key innovations. First, we introduce a tabular-to-text transformation strategy paired with relational data integration schema, enabling the conversion of raw, heterogeneous crash data into enriched, structured textual narratives that retain essential structural and relational context. Second, we apply context-aware data augmentation using a base LLM model to improve narrative coherence while preserving factual integrity. Third, we fine-tune the LLaMA3-8B model for crash severity inference, demonstrating superior performance over baseline approaches, including zero-shot, zero-shot with chain-of-thought prompting, and few-shot learning, with multiple models (GPT-4o, GPT-4o-mini, LLaMA3-70B). Finally, we employ a gradient-based explainability technique to elucidate model decisions at both the individual crash level and across broader risk factor dimensions. This interpretability mechanism enhances transparency and enables targeted road safety interventions by providing deeper insights into the most influential factors.