跳到正文
arXiv cs.AI· Cheng Li, Adhyyan Narang, Jiayi Yuan, John F. Buss, Jina Suh, Devon Sandel-Fernandez, Yulia Tsvetkov, Adam M. Kuczynski, Tim Althoff·· 4 小时前AI 评分38

SimAI:基于心理网络模型的机制性用户模拟框架

SimAI: Mechanistic User Simulation through Psychological Network Models

AI 导读

SimAI 是一个机制性用户模拟框架,通过建模心理因素之间的交互来生成用户响应,并采用图重构目标以图级奖励监督开放式行为。研究团队构建了 PSYCHE 数据集,包含源自 516 个心理治疗案例的 18,576 个画像-网络对。自动评估显示 SimAI 在模拟与行为多样性上优于现有患者模拟器,30 名心理健康专业人士与学员的交互研究也给出最高的对话真实性、求助行为真实度和临床培训实用性评分。

正文 · 原文

View PDF HTML (experimental)

Abstract:Realistic user simulation enables the study of human interactions when direct experimentation is costly or potentially harmful. However, existing simulators largely overlook the psychological mechanisms that drive user behavior. We introduce SimAI, a framework for mechanistic user simulation that models how psychological factors interact to shape user responses. To overcome the challenge of supervising open-ended behavior, we propose a graph reconstruction objective that provides graph-level rewards based on how well simulated conversations reflect the underlying psychological relationships. To support this approach, we construct PSYCHE, a dataset of 18,576 profile-network pairs derived from 516 psychotherapy cases. Automatic evaluations show that SimAI achieves greater simulation and behavioral diversity than existing patient simulators while maintaining strong profile alignment. In an interactive study with 30 mental-health professionals and trainees, SimAI receives the highest average ratings for conversational authenticity, realistic help-seeking behavior, and clinical training utility. Beyond simulation quality, SimAI enables realistic clinical training and uncovers safety failures in prolonged AI interactions with vulnerable users. Code is available at this https URL.
Comments: 47 pages
Subjects: Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)
Cite as: arXiv:2611.21808 [cs.CL]
  (or arXiv:2611.21808v1 [cs.CL] for this version)
  https://doi.org/10.48550/arXiv.2611.21808

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Cheng Li [view email]
[v1] Mon, 16 Nov 2026 19:23:35 UTC (2,018 KB)

来源:arXiv cs.AI · arxiv.org