用大模型助手帮心理健康机构高效制定个性化支持计划。
PeerCoPilot: A Language Model-Powered Assistant for Behavioral Health Organizations
- 基于1300+审核资源构建检索增强生成系统，确保信息可靠。
- 90%以上用户认可该助手，生成内容比普通大模型更精准。
- 已落地于超万人服务的机构，适合一线心理支持人员使用。
行为健康问题（包括心理健康与物质滥用障碍）是美国最主要的疾病负担。同行运营的行为健康组织（PROs）通过结合心理服务与收入、就业、住房等需求支持，为患者提供关键帮助。然而，资金和人力有限，难以满足所有用户需求。为此，我们提出PeerCoPilot——一个基于大语言模型（LLM）的助手，帮助同行提供者制定康复计划、设定分步目标，并定位组织资源以支持目标实现。PeerCoPilot通过包含超过1,300个审核过的资源数据库的检索增强生成流程保障信息可靠性。我们对15名同行提供者和6名服务用户进行了人工评估，发现超过90%的用户支持使用PeerCoPilot。此外，实验证明其提供的信息比基线大模型更可靠、更具体。目前，PeerCoPilot已在服务超10,000名用户的大型机构CSPNJ中由5-10名同行提供者使用，我们正积极推广其应用。
原文摘要 · Abstract (English)
Behavioral health conditions, which include mental health and substance use disorders, are the leading disease burden in the United States. Peer-run behavioral health organizations (PROs) critically assist individuals facing these conditions by combining mental health services with assistance for needs such as income, employment, and housing. However, limited funds and staffing make it difficult for PROs to address all service user needs. To assist peer providers at PROs with their day-to-day tasks, we introduce PeerCoPilot, a large language model (LLM)-powered assistant that helps peer providers create wellness plans, construct step-by-step goals, and locate organizational resources to support these goals. PeerCoPilot ensures information reliability through a retrieval-augmented generation pipeline backed by a large database of over 1,300 vetted resources. We conducted human evaluations with 15 peer providers and 6 service users and found that over 90% of users supported using PeerCoPilot. Moreover, we demonstrated that PeerCoPilot provides more reliable and specific information than a baseline LLM. PeerCoPilot is now used by a group of 5-10 peer providers at CSPNJ, a large behavioral health organization serving over 10,000 service users, and we are actively expanding PeerCoPilot's use.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。