GenPT：通过生成式投射测试实现超越自我报告的可靠LLM心理测量
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
AI总结：
针对自我报告问卷在人格化智能体心理测量中存在的训练语料污染和方向性偏差问题，提出GenPT方法，通过改编投射测试范式并构建三阶段评估流程，实现了更可靠的心理状态测量。
摘要：
自我报告问卷仍然是探测人格化智能体（PC-Agents）心理状态的主流工具。然而，经典工具存在两个众所周知的威胁：来自训练语料的污染以及由社会期望或上下文框架驱动的方向性偏差。为了克服这些方法论瓶颈，我们探讨投射范式是否能够被改编为一种稳健的心理测量工具。我们提出了 extbf{GenPT}（生成式投射测试），它通过新生成的刺激重新表述了TAT、罗夏测试和SCT，并将评估组织为三阶段流程，以导出标准化的心理指标和目标状态。通过评估由CharacterRAG和AnnaAgent配置文件诱导的PC-Agents，我们针对经典问卷基准测试了GenPT的信度和效度。结果表明，问卷在社会期望框架下表现出系统性的方向性偏移，在自杀意念上最为强烈。相比之下，GenPT收集的行为模式保持在对称基线附近。此外，在纵向咨询背景下，当Qwen3作为骨干模型时，基于GenPT的抑郁评估变化幅度比问卷对应方法大约一个数量级。总体而言，GenPT在需要抗污染、偏差对称性和上下文敏感性的场景中补充了自我报告方法。代码和刺激材料可在https://github.com/sci-m-wang/GenPT获取。
英文摘要：
Self-report questionnaires remain the prevailing tool for probing the psychological states of persona-conditioned agents (PC-Agents). However, classical instruments inherit two well-known threats: contamination from training corpora and directional bias driven by social-desirability or contextual framing. To overcome these methodological bottlenecks, we ask whether projective paradigms can be adapted into a robust psychometric tool. We introduce \textbf{GenPT} (Generative Projective Testing), which reformulates TAT, Rorschach, and SCT with newly generated stimuli and organizes assessment as a three-stage pipeline to derive standardized psychological indicators and target states. Evaluating PC-Agents induced via CharacterRAG and AnnaAgent profiles, we benchmark GenPT's reliability and validity against classical questionnaires. The results indicate that questionnaires exhibit systematic directional shifts under social-desirability framing, most strongly on suicide ideation. In contrast, GenPT's collected behavioral patterns stay near the symmetric baseline. Furthermore, under a longitudinal counselling context, GenPT-based depression assessment shifts by roughly an order of magnitude more than the questionnaire counterpart when Qwen3 serves as the backbone. Overall, GenPT complements self-report methods in scenarios where contamination resistance, bias asymmetry, and context sensitivity matter. Code and stimuli can be found at https://github.com/sci-m-wang/GenPT.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
