ALIGN: A Vision-Language Framework for High-Accuracy Accident Location Inference through Geo-Spatial Neural Reasoning
On the map: LLM reasoning → Spatial and embodied reasoning
Abstract (arXiv)
In low- and middle-income countries, public safety and urban planning initiatives frequently face a critical shortage of accurate, location-specific road crash data. Extracting reliable geospatial information from unstructured text requires overcoming the limitations of traditional text-based geocoding tools, which often fail in multilingual environments with ambiguous place descriptions. This study introduces ALIGN (Accident Location Inference through Geo-Spatial Neural Reasoning), a vision-language framework designed to emulate human spatial reasoning to infer precise accident coordinates from unstructured Bangla news reports and map-based cues. A multi stage automated pipeline was developed to process diverse textual and visual data, integrating large language models for cue extraction with vision-language models for map verification. Using an agentic architecture, we modelled an iterative reasoning loop that combines Optical Character Recognition (OCR), grid-based spatial scanning, and a 3-run geometric voting method to mathematically isolate and reduce visual hallucinations. The findings highlight that the multimodal ALIGN framework significantly outperforms traditional text-only geoparsing baselines. For example, the proposed system successfully reduced the mean localization error from an unusable 10.915 km to a sub-kilometer precision of 0.593 km on a validation dataset. Furthermore, testing the framework against official Dhaka Metropolitan Police records confirmed its reliability by achieving a mean error of 0.465 km. The results provide a high-accuracy, training-free foundation for automated crash mapping in data-scarce regions, supporting evidence-driven road-safety policymaking and the integration of multimodal AI in transportation analytics.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 8 of its 54 references that are in the map. First posted on arXiv 9 Nov 2025.
Builds on
8 of 54 references.
References · 8
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
- 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
- 2023Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messagescited by 31
- 2017Location Name Extraction from Targeted Text Streams using Gazetteer-based Statistical Language Modelscited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
- 2025Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
- 2026Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach
- 2025GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning
- 2026m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning
- 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
- 2025RoadBench: Benchmarking MLLMs on Fine-Grained Spatial Understanding and Reasoning under Urban Road Scenarios
- 2025From Pixels to Places: A Systematic Benchmark for Evaluating Image Geolocalization Ability in Large Language Models