Spatial Balancing: Designing an LLM-Powered Spatial Externalization Interface for Iterative Science Communication Writing
arXiv:2509.13742 · doi:10.1145/3800645.3812998
Abstract
Science communication revision requires writers to dynamically balance scientific exposition and narrative engagement - a process where writers often struggle with competing directions. Existing LLM-assisted tools help with co-writing, but offer limited support for navigating this iterative, multi-directional revision process. To address this gap, we designed Spatial Balancing, an exploratory revision environment that maps rhetorical goals and revision strategies onto a two-dimensional spatial canvas for experienced science communication creators with domain expertise but lacking formal professional training. By building a design space of communication strategies and embedding them into a spatial exploratory canvas, our system treats feedback as navigational cues rather than prescriptive judgments. Our findings show that this integrated revision environment helps writers stay focused on writing goals, reason about revision as trajectories, and explore alternatives, which supports greater metacognitive control and confidence without increasing workload. This work highlights the value of spatially externalized revision environments for supporting iterative, reflective thinking during LLM-assisted writing.
DIS '26
References in corpus (11)
- Beware of Metacognitive Laziness: Effects of Generative Artificial Intelligence on Learning Motivation, Processes, and Performance
- Luminate: Structured Generation and Exploration of Design Space with Large Language Models for Human-AI Co-Creation
- A Design Space for Intelligent and Interactive Writing Assistants
- VISAR: A Human-AI Argumentative Writing Assistant with Visual Programming and Rapid Draft Prototyping
- When Teams Embrace AI: Human Collaboration Strategies in Generative Prompting in a Creative Design Task
- ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models
- A Preliminary Exploration of YouTubers' Use of Generative-AI in Content Creation
- Patchview: LLM-Powered Worldbuilding with Generative Dust and Magnet Visualization
- From `Wow' to `Why': Guidelines for Creating the Opening of a Data Video with Cinematic Styles
- Toyteller: AI-powered Visual Storytelling Through Toy-Playing with Character Symbols
- RevTogether: Supporting Science Story Revision with Multiple AI Agents