发表机构
University of Haifa; Bar-Ilan University（海法大学; 巴伊兰大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于心理学三层架构的Deep Persona角色扮演智能体，并设计无参考评估框架，实证发现LLM在情感表达和联合注意上有局限，结构化角色能更贴近人类对话行为。
AI 中文摘要
现有使用大型语言模型（LLMs）进行角色模拟的方法大多依赖浅层的人物描述，这些描述无法在长时间交互中维持连贯的角色行为。我们提出了Deep Persona，这是一种基于心理学基础的三层架构，将角色组织为可观察表达、潜在信念和核心动机驱动等层级，用于构建高度可信的角色扮演智能体。该架构遵循脚本化决定论和有界能动性的原则，将模型限制为一个由结构化内部脚本引导的反应式引擎。我们进一步提出了一种无参考的评估框架，该框架使用既定的心理学临床工具和对抗性压力测试，将对话自然度与经验性人类分布进行基准比较。实证评估显示，虽然LLMs实现了较高的语用流畅性，但在情感表达和联合注意方面表现出系统性局限。此外，我们展示了一个关于两个Deep Persona的案例研究，并使用所提出的框架对其进行评估，证明结构化角色可以产生更接近人类对话行为的交互。
英文摘要
Existing approaches to persona simulation with Large Language Models (LLMs) mostly rely on shallow character descriptions that fail to sustain coherent character behavior across extended interactions. We introduce Deep Persona, a psychologically grounded, three-layered architecture that organizes personas into hierarchical levels of observable expression, latent beliefs, and core motivational drives, for constructing highly convincing role-playing agents. Governed by the principles of scripted determinism and bounded agency, the architecture restricts the model to a reactive engine guided by a structured internal script. We further propose a reference-free evaluation framework that benchmarks dialogue naturalness against empirical human distributions using established psychological clinical instruments and adversarial stress-tests. Empirical evaluation reveals that while LLMs achieve high pragmatic fluency, they exhibit systematic limitations in emotional expression and joint attention. In addition, we present a case study of two Deep Personas and evaluate them using the proposed framework, demonstrating that structured personas can produce interactions that more closely align with human conversational behavior.
