GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908526263140352 |
|---|---|
| author | Yerramilli, Sahiti Pande, Nilay Grover, Rynaa Tamarapalli, Jayant Sravan |
| author_facet | Yerramilli, Sahiti Pande, Nilay Grover, Rynaa Tamarapalli, Jayant Sravan |
| contents | This paper introduces GeoChain, a large-scale benchmark for evaluating step-by-step geographic reasoning in multimodal large language models (MLLMs). Leveraging 1.46 million Mapillary street-level images, GeoChain pairs each image with a 21-step chain-of-thought (CoT) question sequence (over 30 million Q&A pairs). These sequences guide models from coarse attributes to fine-grained localization across four reasoning categories - visual, spatial, cultural, and precise geolocation - annotated by difficulty. Images are also enriched with semantic segmentation (150 classes) and a visual locatability score. Our benchmarking of contemporary MLLMs (GPT-4.1 variants, Claude 3.7, Gemini 2.5 variants) on a diverse 2,088-image subset reveals consistent challenges: models frequently exhibit weaknesses in visual grounding, display erratic reasoning, and struggle to achieve accurate localization, especially as the reasoning complexity escalates. GeoChain offers a robust diagnostic methodology, critical for fostering significant advancements in complex geographic reasoning within MLLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_00785 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning Yerramilli, Sahiti Pande, Nilay Grover, Rynaa Tamarapalli, Jayant Sravan Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning This paper introduces GeoChain, a large-scale benchmark for evaluating step-by-step geographic reasoning in multimodal large language models (MLLMs). Leveraging 1.46 million Mapillary street-level images, GeoChain pairs each image with a 21-step chain-of-thought (CoT) question sequence (over 30 million Q&A pairs). These sequences guide models from coarse attributes to fine-grained localization across four reasoning categories - visual, spatial, cultural, and precise geolocation - annotated by difficulty. Images are also enriched with semantic segmentation (150 classes) and a visual locatability score. Our benchmarking of contemporary MLLMs (GPT-4.1 variants, Claude 3.7, Gemini 2.5 variants) on a diverse 2,088-image subset reveals consistent challenges: models frequently exhibit weaknesses in visual grounding, display erratic reasoning, and struggle to achieve accurate localization, especially as the reasoning complexity escalates. GeoChain offers a robust diagnostic methodology, critical for fostering significant advancements in complex geographic reasoning within MLLMs. |
| title | GeoChain: Multimodal Chain-of-Thought for Geographic Reasoning |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2506.00785 |