Large Language Models in Peer-Run Community Behavioral Health Services: Understanding Peer Specialists and Service Users'Perspectives on Opportunities, Risks, and Mitigation Strategies

2026-02-09

AI Summary

This study investigates the challenges large language models (LLMs) pose to contextuality, trust, and autonomy when introduced into peer-led community behavioral health services. In collaboration with a New Jersey-based peer support organization, the authors employed a comicboarding co-design methodology, engaging 16 peer specialists and 10 service users in workshops to collaboratively develop and evaluate an LLM-powered recommendation system prototype. The work proposes a “lived experience–in-the-loop” design philosophy, positioning LLMs not as clinical tools but as relational collaborators in high-stakes care contexts, with an emphasis on co-constructing trust. The project identifies three key tensions—scalability versus localization, trust maintenance versus relational dynamics, and efficiency gains versus peer autonomy—and outlines corresponding opportunities, risks, and mitigation strategies.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Peer-run organizations (PROs) provide critical, recovery-based behavioral health support rooted in lived experience. As large language models (LLMs) enter this domain, their scale, conversationality, and opacity introduce new challenges for situatedness, trust, and autonomy. Partnering with Collaborative Support Programs of New Jersey (CSPNJ), a statewide PRO in the Northeastern United States, we used comicboarding, a co-design method, to conduct workshops with 16 peer specialists and 10 service users exploring perceptions of integrating an LLM-based recommendation system into peer support. Findings show that depending on how LLMs are introduced, constrained, and co-used, they can reconfigure in-room dynamics by sustaining, undermining, or amplifying the relational authority that grounds peer support. We identify opportunities, risks, and mitigation strategies across three tensions: bridging scale and locality, protecting trust and relational dynamics, and preserving peer autonomy amid efficiency gains. We contribute design implications that center lived-experience-in-the-loop, reframe trust as co-constructed, and position LLMs not as clinical tools but as relational collaborators in high-stakes, community-led care.

Problem

• Large Language Models
• Peer-run organizations
• Behavioral health
• Trust
• Autonomy

Innovation

• large language models
• peer-run organizations
• co-design
• relational collaboration
• lived experience