Effective prompting of generative AI is challenging for many users, particularly in expressing context for comprehension tasks such as explaining spreadsheet formulas, Python code, and text passages. Prompt middleware aims to address this barrier by assisting in prompt construction, but barriers remain for users in expressing adequate control so that they can receive AI-responses that match their preferences. We conduct a formative survey (n=38) investigating user needs for control over AI-generated explanations in comprehension tasks, which uncovers a trade-off between standardized but predictable support for prompting, and adaptive but unpredictable support tailored to the user and task. To explore this trade-off, we implement two prompt middleware approaches: Dynamic Prompt Refinement Control (Dynamic PRC) and Static Prompt Refinement Control (Static PRC). The Dynamic PRC approach generates context-specific UI elements that provide prompt refinements based on the user's prompt and user needs from the AI, while the Static PRC approach offers a preset list of generally applicable refinements. We evaluate these two approaches with a controlled user study (n=16) to assess the impact of these approaches on user control of AI responses for crafting better explanations. Results show a preference for the Dynamic PRC approach as it afforded more control, lowered barriers to providing context, and encouraged exploration and reflection of the tasks, but that reasoning about the effects of different generated controls on the final output remains challenging. Drawing on participant feedback, we discuss design implications for future Dynamic PRC systems that enhance user control of AI responses. Our findings suggest that dynamic prompt middleware can improve the user experience of generative AI workflows by affording greater control and guide users to a better AI response.

翻译：对于许多用户而言，有效提示生成式人工智能颇具挑战，尤其是在为理解任务（如解释电子表格公式、Python代码和文本段落）表达上下文时。提示中间件旨在通过辅助提示构建来解决这一障碍，但用户在表达充分控制以获取符合其偏好的AI响应方面仍面临阻碍。我们开展了一项形成性调查（n=38），探究用户在理解任务中对AI生成解释的控制需求，揭示了标准化但可预测的提示支持与适应用户和任务但不可预测的自适应支持之间的权衡。为探索这一权衡，我们实现了两种提示中间件方法：动态提示精炼控制（Dynamic PRC）和静态提示精炼控制（Static PRC）。Dynamic PRC方法生成特定于上下文的UI元素，基于用户的提示及其对AI的需求提供提示精炼选项；而Static PRC方法则提供一个预设的通用精炼选项列表。我们通过一项受控用户研究（n=16）评估了这两种方法，以衡量它们对用户控制AI响应以生成更好解释的影响。结果显示，用户更倾向于Dynamic PRC方法，因为它提供了更多控制、降低了提供上下文的障碍，并鼓励了对任务的探索与反思，但理解不同生成控制对最终输出的影响仍然具有挑战性。基于参与者反馈，我们讨论了未来增强用户对AI响应控制的Dynamic PRC系统的设计启示。我们的研究结果表明，动态提示中间件能够通过提供更强的控制并引导用户获得更好的AI响应，从而改善生成式AI工作流的用户体验。