Relational Mediators: LLM Chatbots as Boundary Objects in Psychotherapy

TL;DR

This paper introduces a framework for using large language models as adaptive boundary objects in psychotherapy to mediate relational challenges faced by marginalized clients, aiming to improve therapeutic trust and authenticity.

Contribution

It proposes the Dynamic Boundary Mediation Framework, conceptualizing LLMs as mediators that address knowledge gaps, power imbalances, and contextual disconnects in therapy with marginalized clients.

Findings

Identified key relational challenges in therapy for marginalized clients.

Developed the Dynamic Boundary Mediation Framework for LLMs in therapy.

Outlined three mediation types: epistemic, relational, and contextual.

Abstract

As large language models (LLMs) are embedded into mental health technologies, they are often framed either as tools assisting therapists or autonomous therapeutic systems. Such perspectives overlook their potential to mediate relational complexities in therapy, particularly for systemically marginalized clients. Drawing on in-depth interviews with 12 therapists and 12 marginalized clients in China, including LGBTQ+ individuals or those from other marginalized backgrounds, we identify enduring relational challenges: difficulties building trust amid institutional barriers, the burden clients carry in educating therapists about marginalized identities, and challenges sustaining authentic self-disclosure across therapy and daily life. We argue that addressing these challenges requires AI systems capable of actively mediating underlying knowledge gaps, power asymmetries, and contextual disconnects. To this end, we propose the Dynamic Boundary Mediation Framework, which reconceptualizes LLM-enhanced systems as adaptive boundary objects that shift mediating roles across therapeutic stages. The framework delineates three forms of mediation: Epistemic (reducing knowledge asymmetries), Relational (rebalancing power dynamics), and Contextual (bridging therapy-life discontinuities). This framework offers a pathway toward designing relationally accountable AI systems that center the lived realities of marginalized users and more effectively support therapeutic relationships.