🤖 AI Summary
Current generative AI writing tools frequently disrupt the natural writing flow—particularly during complex tasks such as content reorganization and logical cohesion. To address this, we propose Script&Shift, a hierarchical interface paradigm: an upper “scripting” layer enables authors to explicitly articulate writing intentions and structural plans, while a lower “shifting” layer dynamically invokes LLMs for rhetorical refinement and semantic coherence enhancement. This is the first systematic approach to bridge the cognitive gaps among conception, semantics, and expression. The method integrates writing cognition modeling, context-aware prompt engineering, and human-AI collaborative interaction design. User evaluations demonstrate that Script&Shift significantly improves both writing efficiency and ideational divergence, while preserving the naturalness of the writing flow and maintaining authorial agency—effectively mitigating AI-induced workflow interruptions.
📝 Abstract
Good writing is a dynamic process of knowledge transformation, where writers refine and evolve ideas through planning, translating, and reviewing. Generative AI-powered writing tools can enhance this process but may also disrupt the natural flow of writing, such as when using LLMs for complex tasks like restructuring content across different sections or creating smooth transitions. We introduce Script&Shift, a layered interface paradigm designed to minimize these disruptions by aligning writing intents with LLM capabilities to support diverse content development and rhetorical strategies. By bridging envisioning, semantic, and articulatory distances, Script&Shift's interactions allow writers to leverage LLMs for various content development tasks (scripting) and experiment with diverse organization strategies while tailoring their writing for different audiences (shifting). This approach preserves creative control while encouraging divergent and iterative writing. Our evaluation shows that Script&Shift enables writers to creatively and efficiently incorporate LLMs while preserving a natural flow of composition.