IntentFlow: Interactive Support for Communicating Intent with LLMs in Writing Tasks

2025-07-29

AI Summary

In LLM-based writing, users struggle to articulate dynamic, ambiguous, or even subconscious low-level writing intentions—such as strategic preferences—leading to suboptimal prompt-based interaction. Method: We propose IntenTree, an editable and visual intent representation framework that explicitly models intentions as structured components, anchors them to generated text via visual links, and supports real-time iterative refinement and cross-task reuse. It integrates NLP techniques to automatically parse intent elements from prompts and employs an intuitive UI enabling drag-and-drop manipulation, in-place editing, and synchronized updates of intent components. Contribution/Results: User studies demonstrate that IntenTree significantly improves the precision and efficiency of intent specification compared to conventional chat interfaces, enabling generated text to more accurately align with users’ underlying intentions.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Humans and AI: Intelligent User Interfaces
• Knowledge Representation and Reasoning: Preferences

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

While large language models (LLMs) are widely used for writing, users often struggle to express their nuanced and evolving intents through prompt-based interfaces. Intents -- low-level strategies or preferences for achieving a writing goal -- are often vague, fluid, or even subconscious, making it difficult for users to articulate and adjust them. To address this, we present IntentFlow, which supports the communication of dynamically evolving intents throughout LLM-assisted writing. IntentFlow extracts goals and intents from user prompts and presents them as editable interface components, which users can revise, remove, or refine via direct manipulation or follow-up prompts. Visual links connect each component to the output segments it influences, helping users understand model behavior. In a within-subjects study (N=12), participants using IntentFlow, compared to a chat-based baseline, expressed their intents more easily and in detail, engaged in more meaningful actions to communicate intents, such as adjusting and deleting, and produced outputs that better aligned with their evolving intents. We found that editable intent representations help users refine and consolidate a final set of intents, which can be reused across similar tasks to support consistent and transferable LLM-assisted writing.

Problem

• Users struggle to express nuanced intents in LLM writing tasks
• Vague or fluid intents are hard to articulate and adjust
• Existing interfaces lack support for dynamic intent communication

Innovation

• Extracts goals and intents from user prompts
• Presents intents as editable interface components
• Visual links connect intents to output segments