PersonaMail: Learning and Adapting Personal Communication Preferences for Context-Aware Email Writing

2026-02-19

AI Summary

This work addresses the limitations of current large language models in email writing assistance, which often fail to accurately capture nuanced aspects of tone, interpersonal dynamics, and contextual cues, leading to generated content misaligned with the user’s communicative intent. To overcome this, we propose a context-aware personalized email writing system that explicitly models communicative intent through structured representations, supports multi-granularity tone editing, and incorporates a strategy memory mechanism to reuse effective phrasing across emails. By moving beyond generic text generation paradigms, our approach significantly enhances both writing efficiency and user satisfaction during initial and repeated use, demonstrating its effectiveness and practicality in real-world interpersonal communication scenarios.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent Communication

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

LLM-assisted writing has seen rapid adoption in interpersonal communication, yet current systems often fail to capture the subtle tones essential for effectiveness. Email writing exemplifies this challenge: effective messages require careful alignment with intent, relationship, and context beyond mere fluency. Through formative studies, we identified three key challenges: articulating nuanced communicative intent, making modifications at multiple levels of granularity, and reusing effective tone strategies across messages. We developed PersonaMail, a system that addresses these gaps through structured communication factor exploration, granular editing controls, and adaptive reuse of successful strategies. Our evaluation compared PersonaMail against standard LLM interfaces, and showed improved efficiency in both immediate and repeated use, alongside higher user satisfaction. We contribute design implications for AI-assisted communication systems that prioritize interpersonal nuance over generic text generation.

Problem

• LLM-assisted writing
• communication preferences
• email writing
• interpersonal nuance
• context-aware

Innovation

• context-aware writing
• personalized communication
• granular editing
• adaptive reuse
• LLM-assisted email