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.

翻译：随着大型语言模型（LLM）被融入心理健康技术，它们通常被定位为辅助治疗师的工具或自主治疗系统。这类视角忽视了它们在治疗中调解关系复杂性的潜力，特别是对于系统性边缘化的来访者而言。基于对中国12名治疗师和12名边缘化来访者（包括LGBTQ+个体或其他边缘背景者）的深度访谈，我们识别出持久存在的关系挑战：在制度障碍中建立信任的困难、来访者在教育治疗师理解边缘身份方面承受的负担，以及在治疗与日常生活中维持真实自我表露的挑战。我们认为，应对这些挑战需要能够主动调解潜在知识鸿沟、权力不对称和情境脱节的AI系统。为此，我们提出动态边界调解框架，该框架将LLM增强系统重新概念化为适应性边界对象，能够在不同治疗阶段转换中介角色。该框架阐述了三种调解形式：认知性（减少知识不对称）、关系性（重新平衡权力动态）和情境性（弥合治疗与生活的断裂）。这一框架为设计具有关系责任性的AI系统提供了路径，此类系统以边缘化用户的真实生活经验为中心，并能更有效地支持治疗关系。