Low-dimensional visualizations, or "projection maps," are widely used in scientific and creative domains to interpret large-scale and complex datasets. These visualizations not only aid in understanding existing knowledge spaces but also implicitly guide exploration into unknown areas. Although techniques such as t-SNE and UMAP can generate these maps, there exists no systematic method for leveraging them to generate new content. To address this, we introduce MapExplorer, a novel knowledge discovery task that translates coordinates within any projection map into coherent, contextually aligned textual content. This allows users to interactively explore and uncover insights embedded in the maps. To evaluate the performance of MapExplorer methods, we propose Atometric, a fine-grained metric inspired by ROUGE that quantifies logical coherence and alignment between generated and reference text. Experiments on diverse datasets demonstrate the versatility of MapExplorer in generating scientific hypotheses, crafting synthetic personas, and devising strategies for attacking large language models-even with simple baseline methods. By bridging visualization and generation, our work highlights the potential of MapExplorer to enable intuitive human-AI collaboration in large-scale data exploration.
View on arXiv@article{zhang2025_2412.18673,
title={ MapExplorer: New Content Generation from Low-Dimensional Visualizations },
author={ Xingjian Zhang and Ziyang Xiong and Shixuan Liu and Yutong Xie and Tolga Ergen and Dongsub Shim and Hua Xu and Honglak Lee and Qiaozhu Me },
journal={arXiv preprint arXiv:2412.18673},
year={ 2025 }
}