# Comparing Sentence-Level Suggestions to Message-Level Suggestions in AI-Mediated Communication

## TL;DR

This study compares sentence-level and message-level AI suggestions in communication, finding message-level suggestions improve speed and satisfaction, while sentence-level suggestions enhance user agency, informing better system design.

## Contribution

It provides empirical insights into the trade-offs between sentence- and message-level suggestions in AI-mediated communication systems.

## Key findings

- Message-level suggestions lead to faster responses and higher satisfaction.
- Sentence-level suggestions preserve user agency but require more planning.
- Message-level suggestions produce more helpful final texts.

## Abstract

Traditionally, writing assistance systems have focused on short or even single-word suggestions. Recently, large language models like GPT-3 have made it possible to generate significantly longer natural-sounding suggestions, offering more advanced assistance opportunities. This study explores the trade-offs between sentence- vs. message-level suggestions for AI-mediated communication. We recruited 120 participants to act as staffers from legislators' offices who often need to respond to large volumes of constituent concerns. Participants were asked to reply to emails with different types of assistance. The results show that participants receiving message-level suggestions responded faster and were more satisfied with the experience, as they mainly edited the suggested drafts. In addition, the texts they wrote were evaluated as more helpful by others. In comparison, participants receiving sentence-level assistance retained a higher sense of agency, but took longer for the task as they needed to plan the flow of their responses and decide when to use suggestions. Our findings have implications for designing task-appropriate communication assistance systems.