@inproceedings{8eddcf37174e49969297b4e5b29059ed,
title = "Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation",
abstract = "AI agents are increasingly tasked with making proactive suggestions in online spaces where groups collaborate, yet risk being unhelpful or even annoying if they fail to match group preferences or behave in socially inappropriate ways. Fortunately, group spaces have a rich history of prior interactions and affordances for social feedback that can support grounding an agent's generations to a group's interests and norms. We present Social-RAG, a workflow for socially grounding agents that retrieves context from prior group interactions, selects relevant social signals, and feeds them into a language model to generate messages in a socially aligned manner. We implement this in PaperPing, a system for posting paper recommendations in group chat, leveraging social signals determined from formative studies with 39 researchers. From a three-month deployment in 18 channels reaching 500+ researchers, we observed PaperPing posted relevant messages in groups without disrupting their existing social practices, fostering group common ground.",
keywords = "AI agent, group communication, large language models, recommender systems, retrieval augmented generation",
author = "Ruotong Wang and Xinyi Zhou and Lin Qiu and Chang, \{Joseph Chee\} and Jonathan Bragg and Zhang, \{Amy X.\}",
note = "Publisher Copyright: {\textcopyright} 2025 Copyright held by the owner/author(s).; 2025 CHI Conference on Human Factors in Computing Systems, CHI 2025 ; Conference date: 26-04-2025 Through 01-05-2025",
year = "2025",
month = apr,
day = "26",
doi = "10.1145/3706598.3713749",
language = "English",
series = "Conference on Human Factors in Computing Systems - Proceedings",
publisher = "Association for Computing Machinery",
booktitle = "CHI 2025 - Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems",
address = "United States",
}