MapIQ: Evaluating Multimodal Large Language Models for Map Question Answering

Varun Srivastava, Fan Lei, Srija Mukhopadhyay, Vivek Gupta, Ross Maciejewski

Keywords: Large Language Models, Visual Question Answering, Maps, Geospatial Analysis, Visual Analytics, Benchmark Dataset

TL;DR: We introduce MapIQ, a benchmark for evaluating multimodal large language models (MLLMs) on map-based visual question answering (Map-VQA) across three map types, also assessing their robustness to map desing variations.

Abstract: Recent advancements in multimodal large language models (MLLMs) have driven researchers to explore how well these models read data visualizations, e.g., bar charts, scatter plots. More recently, attention has shifted to visual question answering with maps (Map-VQA). However, Map-VQA research has primarily focused on choropleth maps, which cover only a limited range of thematic categories and visual analytical tasks. To address these gaps, we introduce MapIQ, a benchmark dataset comprising 14,706 question-answer pairs across three map types—choropleth maps, cartograms, and proportional symbol maps spanning topics from six distinct themes (e.g., housing, crime). We evaluate multiple MLLMs using six visual analytical tasks, comparing their performance against one another and a human baseline. An additional experiment examining the impact of map design changes (e.g., altered color schemes, modified legend designs, and removal of map elements) provides insights into the robustness and sensitivity of MLLMs, their reliance on internal geographic knowledge, and potential avenues for improving Map-VQA performance.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 650