# EG-ARSA: An Expert-Grounded Open Model for Visual Road Safety Auditing in Low-Resource Settings

arXiv: https://arxiv.org/abs/2608.23563 · HTML: https://mlsanity.com/paper/2608.23563/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 48 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 30 of 31)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Long-tail learning via logit adjustment](https://mlsanity.com/paper/2007.07314/) (2020)
- [Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision](https://mlsanity.com/paper/2312.09390/) (2023)
- [Balanced Meta-Softmax for Long-Tailed Visual Recognition](https://mlsanity.com/paper/2007.10740/) (2020)
- [Scaling Down to Scale Up: A Guide to Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2303.15647/) (2023)
- [Active Data Curation Effectively Distills Large-Scale Multimodal Models](https://mlsanity.com/paper/2411.18674/) (2024)
- [A Survey on Efficient Vision-Language Models](https://mlsanity.com/paper/2504.09724/) (2025)
- [Escaping Collapse: The Strength of Weak Data for Large Language Model Training](https://mlsanity.com/paper/2502.08924/) (2025)
- [FARSA: Fully Automated Roadway Safety Assessment](https://mlsanity.com/paper/1901.06013/) (2019)
- [From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning](https://mlsanity.com/paper/2410.06456/) (2024)
- [V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?](https://mlsanity.com/paper/2408.10872/) (2024)
- [Examining the Commitments and Difficulties Inherent in Multimodal Foundation Models for Street View Imagery](https://mlsanity.com/paper/2408.12821/) (2024)
- [Can Generalist Vision Language Models (VLMs) Rival Specialist Medical VLMs? Benchmarking and Strategic Insights](https://mlsanity.com/paper/2506.17337/) (2025)
- [Evaluating Computer Vision Techniques for Urban Mobility on Large-Scale, Unconstrained Roads](https://mlsanity.com/paper/2109.05226/) (2021)
- [Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations](https://mlsanity.com/paper/2508.02047/) (2025)
- [Multi-Agent Visual-Language Reasoning for Comprehensive Highway Scene Understanding](https://mlsanity.com/paper/2508.17205/) (2025)
- [Dynamic loss balancing and sequential enhancement for road-safety assessment and traffic scene classification](https://mlsanity.com/paper/2211.04165/) (2022)
- [Mapping road safety features from streetview imagery: A deep learning approach](https://mlsanity.com/paper/1907.12647/) (2019)
- [HazardNet: A Small-Scale Vision Language Model for Real-Time Traffic Safety Detection at Edge Devices](https://mlsanity.com/paper/2502.20572/) (2025)

## Abstract (arXiv)

Road traffic injuries remain a major challenge in low- and middle-income countries, where proactive road safety auditing is limited by incomplete crash records, shortages of qualified auditors, and the high cost of large-scale field inspections. To address this problem, we propose Expert-Grounded Distillation (EGD), a novel artificial intelligence framework that transfers institutional road safety expertise into a compact vision-language model for scalable visual road safety auditing. The key innovation is a quantified expert-grounding stage in which the teacher vision-language model is calibrated against authoritative field audits. Large-scale annotation is permitted only after the teacher reaches substantial agreement with expert risk assessments (Cohen's kappa = 0.74). The calibrated teacher then generates structured supervision that is distilled into an 8-billion-parameter student vision-language model using Low-Rank Adaptation and a single leakage-free prompt. We also introduce Bangladesh Road Safety Audit (BD-ARSA), the first open, expert-grounded Bangladeshi visual road safety audit dataset containing 21,947 image-audit records with near-national coverage, and Expert-Grounded Road Safety Auditor (EG-ARSA), the first vision-language model developed specifically for this task. Experimental results show that grounded fine-tuning substantially improves ordinal risk assessment over the zero-shot baseline, while blind expert evaluation demonstrates that the compact student outperforms both its 31 billion-parameter teacher and Gemini-2.5-Flash. These findings demonstrate that EGD provides an effective and scalable engineering solution for proactive road safety auditing in resource-constrained environments.