Content-Driven Local Response: Supporting Sentence-Level and Message-Level Mobile Email Replies With and Without AI

2025-02-10

AI Summary

AI-assisted reply generation in mobile email faces a fundamental trade-off between efficiency and user control. This paper introduces Content-Driven Localized Responses (CDLR), a novel paradigm that enables fine-grained, context-aware regulation of AI involvement via a microtask-inspired mobile UI: users dynamically trigger sentence-level localized suggestions or message-level global generation by tapping individual email sentences. Core technical contributions include a lightweight on-device triggering logic, a context-aware prompting mechanism grounded in interaction behavior modeling, and a human-AI collaborative decision-making interface framework. A user study (N=126) demonstrates that CDLR significantly reduces input effort (−42%) and error rate (−37%) compared to both manual composition and fully automated AI generation, while simultaneously increasing users’ perceived autonomy over AI intervention (+58%) and flexibility in task adaptation.

Technology Category

• Humans and AI: Interaction Techniques and Devices
• Natural Language Processing: Generation
• Intelligent Robots: Embodied AI

Application Category

• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Mobile emailing demands efficiency in diverse situations, which motivates the use of AI. However, generated text does not always reflect how people want to respond. This challenges users with AI involvement tradeoffs not yet considered in email UIs. We address this with a new UI concept called Content-Driven Local Response (CDLR), inspired by microtasking. This allows users to insert responses into the email by selecting sentences, which additionally serves to guide AI suggestions. The concept supports combining AI for local suggestions and message-level improvements. Our user study (N=126) compared CDLR with manual typing and full reply generation. We found that CDLR supports flexible workflows with varying degrees of AI involvement, while retaining the benefits of reduced typing and errors. This work contributes a new approach to integrating AI capabilities: By redesigning the UI for workflows with and without AI, we can empower users to dynamically adjust AI involvement.

Problem

• Enhancing mobile email reply efficiency
• Balancing AI-generated text and user intent
• Integrating AI in email UIs flexibly

Innovation

• UI redesign for AI integration
• Content-Driven Local Response
• Dynamic AI involvement adjustment