2024/11/04 by Ruotong Wang, Xinyi Zhou, Wang, Ruotong +9 · 1 voice · 6 citations
Computer Science · Psychology · #FOS: Computer and information sciences #Human-Automation Interaction and Safety #Human-Computer Interaction (cs.HC) #cs.HC
paper · pdf · doi:10.48550/arxiv.2411.02353
openalex publication_date 2024/11/04 · arxiv published 2024/11/04 · openalex created_date 2024/11/15 · arxiv updated 2025/02/19 · openalex updated_date 2026/07/28
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.