Automated Label Placement on Maps via Large Language Models
Harry Shomer, Jiejun Xu

TL;DR
This paper introduces a novel approach for automated map label placement using large language models, leveraging data editing and retrieval-augmented generation to improve scalability and adherence to cartographic standards.
Contribution
It formulates label placement as a data editing task with LLMs, introduces the MAPLE dataset, and demonstrates effective, context-aware label placement through retrieval and instruction tuning.
Findings
LLMs can generate accurate label coordinates aligned with cartographic standards.
Retrieval-augmented prompts improve LLM performance in label placement.
The framework is scalable and adaptable to diverse map types.
Abstract
Label placement is a critical aspect of map design, serving as a form of spatial annotation that directly impacts clarity and interpretability. Despite its importance, label placement remains largely manual and difficult to scale, as existing automated systems struggle to integrate cartographic conventions, adapt to context, or interpret labeling instructions. In this work, we introduce a new paradigm for automatic label placement (ALP) that formulates the task as a data editing problem and leverages large language models (LLMs) for context-aware spatial annotation. To support this direction, we curate MAPLE, the first known benchmarking dataset for evaluating ALP on real-world maps, encompassing diverse landmark types and label placement annotations from open-source data. Our method retrieves labeling guidelines relevant to each landmark type leveraging retrieval-augmented generation…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGeographic Information Systems Studies · Data Visualization and Analytics · Constraint Satisfaction and Optimization
