LMCanvas: Object-Oriented Interaction to Personalize Large Language Model-Powered Writing Environments
This addresses the need for writers to personalize their writing environments to avoid switching between multiple interfaces, but it is incremental as it builds on existing LLM tool concepts.
The authors tackled the problem of limited personalization in LLM-powered writing interfaces by proposing LMCanvas, an interface that allows writers to create custom tools using interactive blocks on a canvas, though no concrete results or numbers are provided as it is a design proposal.
Large language models (LLMs) can enhance writing by automating or supporting specific tasks in writers' workflows (e.g., paraphrasing, creating analogies). Leveraging this capability, a collection of interfaces have been developed that provide LLM-powered tools for specific writing tasks. However, these interfaces provide limited support for writers to create personal tools for their own unique tasks, and may not comprehensively fulfill a writer's needs -- requiring them to continuously switch between interfaces during writing. In this work, we envision LMCanvas, an interface that enables writers to create their own LLM-powered writing tools and arrange their personal writing environment by interacting with "blocks" in a canvas. In this interface, users can create text blocks to encapsulate writing and LLM prompts, model blocks for model parameter configurations, and connect these to create pipeline blocks that output generations. In this workshop paper, we discuss the design for LMCanvas and our plans to develop this concept.