让创意工作流中的生成式AI保持上下文一致，提升创作效率与可控性。
Orchid: Orchestrating Context Across Creative Workflows with Generative AI
- 通过显式引用、内联选择等方式管理项目、个人和风格等多维度上下文。
- 用户在任务中产出更创新且可行的结果，意图与AI响应对齐度更高。
- 适合需要跨会话、跨模型协作的创作者，尤其适合复杂创意项目。
上下文对人与生成式AI之间的有意义交互至关重要。然而主流工具在跨多轮交互、会话及模型的创作工作流中，缺乏有效的上下文协调能力。重复描述先前内容、管理多样产物、应对上下文漂移等问题使用户负担加重，模糊创作意图，抑制创造力。为此，我们提出Orchid系统，为用户提供指定、引用和监控上下文的交互能力。具体包括：（1）定义与项目、个人身份及风格相关的上下文；（2）通过显式提及、内联选择或隐式定位进行引用；（3）可视化追踪各交互步骤所分配的上下文。在12名参与者的对照实验中，使用Orchid完成创意任务的用户相比基线工具（网页搜索、LLM聊天、数字笔记），产出更具新颖性和可行性结果，报告更高的意图对齐度、感知控制力与透明度。通过聚焦上下文协调，Orchid为支持复杂迭代工作流的下一代生成式AI工具提供了切实路径，助力创作者与AI持续对齐，释放创作潜力。
原文摘要 · Abstract (English)
Context is critical for meaningful interactions between people and Generative AI (GenAI). Yet mainstream tools offer limited means to orchestrate it, particularly across workflows that span multiple interactions, sessions, and models, as often occurs in creative projects. Re specifying prior details, juggling diverse artifacts, and dealing with context drift overwhelm users, obscure intent, and curtail creativity. To address these challenges, we present Orchid, a system that gives its users affordances to specify, reference, and monitor context throughout evolving workflows. Specifically, Orchid enables users to (1) specify context related to the project, themselves, and different styles, (2) reference these via explicit mentions, inline selection, or implicit grounding, and (3) monitor context assigned to different interactions across the workflow. In a within-subjects study (n=12), participants using Orchid to execute creative tasks (compared to a baseline toolkit of web search, LLM-based chat, and digital notebooks) produced more novel and feasible outcomes, reporting greater alignment between their intent and the AI's responses, higher perceived control, and increased transparency. By prioritizing context orchestration, Orchid offers an actionable step toward next generation GenAI tools that support complex, iterative workflows - enabling creators and AI to stay aligned and augment their creative potential.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。