MASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological Counseling
作者: Shixin Peng, Kun Jiang, Jiaxing Zheng, Qihao Yang, Jingying Chen
分类: cs.AI
发布日期: 2026-10-06
💡 一句话要点
提出MASC框架以解决心理咨询中客户角色扮演一致性问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 心理咨询 角色扮演 多智能体系统 自校准 大五人格 情感表达 一致性验证
📋 核心要点
- 现有的角色扮演方法依赖静态提示,容易导致客户角色的一致性和心理状态不稳定。
- MASC框架通过构造引导生成和闭环校准机制,确保客户在对话中的心理一致性。
- 实验结果显示,MASC在多个一致性指标上超越了现有方法,异构配置表现最佳。
📝 摘要(中文)
大型语言模型在心理咨询研究和顾问培训中被广泛应用,但可靠的模拟需要客户在长时间交互中保持心理一致性。现有角色扮演方法主要依赖静态的个人资料提示,可能导致角色漂移、不切实际的合作性以及心理状态、沟通行为和情感的不一致。本文提出MASC,一个多智能体自校准框架,通过潜在构造对齐实现心理咨询中客户角色扮演的一致性。MASC结合了构造引导生成、协作优化、一致性验证和基于记忆的修正,形成一个闭环校准机制,能够在对话展开过程中检测和纠正不一致。此外,我们引入了CRPC-Bench,一个涵盖会话级个人资料信息和大五人格特质的基准,包含38个动机访谈客户档案,增强了人格和情感注释。实验表明,MASC在个人资料、一致性等方面优于现有方法。
🔬 方法详解
问题定义:本文旨在解决心理咨询中客户角色扮演的一致性问题,现有方法存在角色漂移和心理状态不一致等痛点。
核心思路:MASC框架通过潜在构造对齐和闭环校准机制,实时检测和修正对话中的不一致性,从而保持客户角色的心理一致性。
技术框架:MASC的整体架构包括构造引导生成、协作优化、一致性验证和基于记忆的修正四个主要模块,形成闭环校准流程。
关键创新:MASC的核心创新在于其闭环校准机制,能够在对话过程中动态调整客户角色,确保心理状态的一致性,这与传统静态方法形成鲜明对比。
关键设计:在设计中,MASC采用了特定的损失函数来评估一致性,并通过记忆模块存储和回顾对话历史,以支持实时的角色调整。实验中使用了大五人格特质作为评估标准,确保了多维度的角色一致性。
🖼️ 关键图片
📊 实验亮点
实验结果表明,MASC在个人资料、一致性和情感表达等方面均优于现有方法,特别是在异构配置下,整体性能提升显著,展示了该框架的有效性和实用性。
🎯 应用场景
MASC框架可广泛应用于心理咨询领域,尤其是在AI辅助的咨询训练和研究中,帮助提升模拟客户的心理一致性和交互质量。未来,该框架有望推动心理健康领域的智能化发展,改善咨询效果。
📄 摘要(原文)
Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to remain psychologically coherent across extended interactions. Existing role-playing methods largely rely on static profile prompts and may exhibit persona drift, unrealistic cooperativeness, or inconsistent psychological states, communicative actions, and emotions. Existing evaluations also lack a unified testbed for both stable client characteristics and evolving psychological dynamics. We propose MASC, a Multi-Agent Self-Calibration framework with latent construct alignment for consistent client role-playing in psychological counseling. MASC combines construct-guided generation, collaborative refinement, consistency verification, and memory-based revision in a closed calibration loop that detects and corrects inconsistencies as dialogue unfolds. We further introduce CRPC-Bench, a benchmark covering session-level profile information and Big-Five personality traits, as well as turn-level psychological state, communicative action, and emotion expression. CRPC-Bench contains 38 motivational interviewing client profiles augmented with personality and emotion annotations. Experiments show that MASC outperforms existing methods across profile, personality, receptivity, and turn-level consistency, with the heterogeneous configuration achieving the strongest overall performance. MASC and CRPC-Bench provide a unified foundation for developing and evaluating psychologically coherent client simulations for AI-assisted counseling research and training.