MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models

• URL: http://arxiv.org/abs/2501.00316v1
• Date: Tue, 31 Dec 2024 07:20:32 GMT
• Title: MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models
• Authors: Mahir Labib Dihan, Md Tanvir Hassan, Md Tanvir Parvez, Md Hasebul Hasan, Md Almash Alam, Muhammad Aamir Cheema, Mohammed Eunus Ali, Md Rizwan Parvez,
• Abstract summary: We introduce MapEval, a benchmark designed to assess diverse and complex map-based user queries with geo-spatial reasoning. MapEval consists of 700 unique multiple-choice questions about locations across 180 cities and 54 countries. Our detailed analyses provide insights into the strengths and weaknesses of current models, though all models still fall short of human performance by more than 20% on average. This gap highlights MapEval's critical role in advancing general-purpose foundation models with stronger geo-spatial understanding.
• Score: 7.422346909538787
• License:
• Abstract: Recent advancements in foundation models have enhanced AI systems' capabilities in autonomous tool usage and reasoning. However, their ability in location or map-based reasoning - which improves daily life by optimizing navigation, facilitating resource discovery, and streamlining logistics - has not been systematically studied. To bridge this gap, we introduce MapEval, a benchmark designed to assess diverse and complex map-based user queries with geo-spatial reasoning. MapEval features three task types (textual, API-based, and visual) that require collecting world information via map tools, processing heterogeneous geo-spatial contexts (e.g., named entities, travel distances, user reviews or ratings, images), and compositional reasoning, which all state-of-the-art foundation models find challenging. Comprising 700 unique multiple-choice questions about locations across 180 cities and 54 countries, MapEval evaluates foundation models' ability to handle spatial relationships, map infographics, travel planning, and navigation challenges. Using MapEval, we conducted a comprehensive evaluation of 28 prominent foundation models. While no single model excelled across all tasks, Claude-3.5-Sonnet, GPT-4o, and Gemini-1.5-Pro achieved competitive performance overall. However, substantial performance gaps emerged, particularly in MapEval, where agents with Claude-3.5-Sonnet outperformed GPT-4o and Gemini-1.5-Pro by 16% and 21%, respectively, and the gaps became even more amplified when compared to open-source LLMs. Our detailed analyses provide insights into the strengths and weaknesses of current models, though all models still fall short of human performance by more than 20% on average, struggling with complex map images and rigorous geo-spatial reasoning. This gap highlights MapEval's critical role in advancing general-purpose foundation models with stronger geo-spatial understanding.

Related papers

• Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework [59.42946541163632]
  We introduce a comprehensive geolocation framework with three key components. GeoComp, a large-scale dataset; GeoCoT, a novel reasoning method; and GeoEval, an evaluation metric. We demonstrate that GeoCoT significantly boosts geolocation accuracy by up to 25% while enhancing interpretability.
  arXiv  Detail & Related papers  (2025-02-19T14:21:25Z)
• PEACE: Empowering Geologic Map Holistic Understanding with MLLMs [64.58959634712215]
  Geologic map, as a fundamental diagram in geology science, provides critical insights into the structure and composition of Earth's subsurface and surface. Despite their significance, current Multimodal Large Language Models (MLLMs) often fall short in geologic map understanding. To quantify this gap, we construct GeoMap-Bench, the first-ever benchmark for evaluating MLLMs in geologic map understanding.
  arXiv  Detail & Related papers  (2025-01-10T18:59:42Z)
• GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks [84.86699025256705]
  We present GEOBench-VLM, a benchmark specifically designed to evaluate Vision-Language Models (VLMs) on geospatial tasks. Our benchmark features over 10,000 manually verified instructions and covers a diverse set of variations in visual conditions, object type, and scale. We evaluate several state-of-the-art VLMs to assess their accuracy within the geospatial context.
  arXiv  Detail & Related papers  (2024-11-28T18:59:56Z)
• TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior [70.84644266024571]
  We propose to train a perception model to "see" standard definition maps (SDMaps) We encode SDMap elements into neural spatial map representations and instance tokens, and then incorporate such complementary features as prior information. Based on the lane segment representation framework, the model simultaneously predicts lanes, centrelines and their topology.
  arXiv  Detail & Related papers  (2024-11-22T06:13:42Z)
• MAPWise: Evaluating Vision-Language Models for Advanced Map Queries [47.15503716894445]
  This study investigates the efficacy of vision-language models (VLMs) in answering questions based on maps. We introduce a novel map-based question-answering benchmark, consisting of maps from three geographical regions (United States, India, China) Our benchmark incorporates 43 diverse question templates, requiring nuanced understanding of relative spatial relationships, intricate map features, and complex reasoning.
  arXiv  Detail & Related papers  (2024-08-30T20:57:34Z)
• Segment Anything Model Can Not Segment Anything: Assessing AI Foundation Model's Generalizability in Permafrost Mapping [19.307294875969827]
  This paper introduces AI foundation models and their defining characteristics. We evaluate the performance of large AI vision models, especially Meta's Segment Anything Model (SAM) The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping.
  arXiv  Detail & Related papers  (2024-01-16T19:10:09Z)
• Assessment of a new GeoAI foundation model for flood inundation mapping [4.312965283062856]
  This paper evaluates the performance of the first-of-its-kind geospatial foundation model, IBM-NASA's Prithvi, to support a crucial geospatial analysis task: flood inundation mapping. A benchmark dataset, Sen1Floods11, is used in the experiments, and the models' predictability, generalizability, and transferability are evaluated. Results show the good transferability of the Prithvi model, highlighting its performance advantages in segmenting flooded areas in previously unseen regions.
  arXiv  Detail & Related papers  (2023-09-25T19:50:47Z)
• A General Purpose Neural Architecture for Geospatial Systems [142.43454584836812]
  We present a roadmap towards the construction of a general-purpose neural architecture (GPNA) with a geospatial inductive bias. We envision how such a model may facilitate cooperation between members of the community.
  arXiv  Detail & Related papers  (2022-11-04T09:58:57Z)
• OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping [15.419052489797775]
  OpenEarthMap is a benchmark dataset for global high-resolution land cover mapping. It consists of 2.2 million segments of 5000 aerial and satellite images covering 97 regions from 44 countries across 6 continents.
  arXiv  Detail & Related papers  (2022-10-19T17:20:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.