MAPWise: Evaluating Vision-Language Models for Advanced Map Queries

TL;DR

This paper introduces MAPWise, a new benchmark for evaluating vision-language models on complex map-based questions, revealing current limitations and guiding future improvements in spatial reasoning tasks.

Contribution

It presents a novel map question-answering benchmark with diverse maps and questions, facilitating research on VLMs' spatial understanding capabilities.

Findings

VLMs show significant gaps in map-based reasoning.

The benchmark covers diverse geographical regions and question types.

Insights suggest directions for enhancing VLM spatial reasoning.

Abstract

Vision-language models (VLMs) excel at tasks requiring joint understanding of visual and linguistic information. A particularly promising yet under-explored application for these models lies in answering questions based on various kinds of maps. This study investigates the efficacy of VLMs in answering questions based on choropleth maps, which are widely used for data analysis and representation. To facilitate and encourage research in this area, we introduce a novel map-based question-answering benchmark, consisting of maps from three geographical regions (United States, India, China), each containing 1000 questions. Our benchmark incorporates 43 diverse question templates, requiring nuanced understanding of relative spatial relationships, intricate map features, and complex reasoning. It also includes maps with discrete and continuous values, encompassing variations in color-mapping, category ordering, and stylistic patterns, enabling comprehensive analysis. We evaluate the performance of multiple VLMs on this benchmark, highlighting gaps in their abilities and providing insights for improving such models.