Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916621170245632 |
|---|---|
| author | Wang, Ruotong Zhou, Xinyi Qiu, Lin Chang, Joseph Chee Bragg, Jonathan Zhang, Amy X. |
| author_facet | Wang, Ruotong Zhou, Xinyi Qiu, Lin Chang, Joseph Chee Bragg, Jonathan Zhang, Amy X. |
| contents | 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 \textsc{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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_02353 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation Wang, Ruotong Zhou, Xinyi Qiu, Lin Chang, Joseph Chee Bragg, Jonathan Zhang, Amy X. Human-Computer Interaction 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 \textsc{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. |
| title | Social-RAG: Retrieving from Group Interactions to Socially Ground AI Generation |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2411.02353 |