Research

Paper

AI LLM February 19, 2026

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

Authors

Rui Yao, Qiuyuan Ren, Felicia Fang-Yi Tan, Chen Yang, Xiaoyu Zhang, Shengdong Zhao

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.

Metadata

arXiv ID: 2602.17340
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-02-19
Fetched: 2026-02-21 18:51

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.17340v1</id>\n    <title>PersonaMail: Learning and Adapting Personal Communication Preferences for Context-Aware Email Writing</title>\n    <updated>2026-02-19T13:16:01Z</updated>\n    <link href='https://arxiv.org/abs/2602.17340v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.17340v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <published>2026-02-19T13:16:01Z</published>\n    <arxiv:comment>21 pages, 5 figures. Accepted to the 31st International Conference on Intelligent User Interfaces (IUI 26), March 23-26, 2026, Paphos, Cyprus</arxiv:comment>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Rui Yao</name>\n    </author>\n    <author>\n      <name>Qiuyuan Ren</name>\n    </author>\n    <author>\n      <name>Felicia Fang-Yi Tan</name>\n    </author>\n    <author>\n      <name>Chen Yang</name>\n    </author>\n    <author>\n      <name>Xiaoyu Zhang</name>\n    </author>\n    <author>\n      <name>Shengdong Zhao</name>\n    </author>\n    <arxiv:doi>10.1145/3742413.3789123</arxiv:doi>\n    <link href='https://doi.org/10.1145/3742413.3789123' rel='related' title='doi'/>\n  </entry>"
}