1
Natural Language Processing Psychometrics
用NLP重新定义心理测量，从语言中解码人格与认知特征，交叉学科新视角。
arXiv:2608.07316v1 Announce Type: cross Abstract: Natural Language Processing (NLP) models predicting mental health outcomes rarely specify what they …
2
When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
当AI化身心理治疗来访者，研究发现前沿模型会构建出有内心冲突的自传叙事，揭示了越狱攻击的新可能。
arXiv:2512.04124v4 Announce Type: replace-cross Abstract: Frontier language models increasingly participate in conversations about distress and mental…
3
Multilayer Q-Matrix-Embedded Neural Network for Cognitive Diagnosis (M-QCDNet): Structure-Aware Deep Learning Architecture for Psychometric Interpretability
把Q矩阵嵌入多层神经网络，让认知诊断既保留深度学习的精度，又获得心理测量学的可解释性。
arXiv:2607.01278v1 Announce Type: new Abstract: The research proposes a multilayer Q-matrix-embedded neural network for cognitive diagnosis (M-QCDNet)…
4
The Dual Nature of LLM Persona: Aggregated Tendencies and Frame-Dependent Geometry
论文揭示LLM人格评估中聚合分数忽略结构相关性的双重本质：聚合倾向与框架依赖几何
arXiv:2607.02368v1 Announce Type: cross Abstract: Evaluations of LLM personas via psychometric questionnaires typically rely on aggregate scores, disc…
5
FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents
金融AI代理稳定性评估基准，长期追踪心理测量指标，确保智能体始终遵循预设行为指令。
arXiv:2606.31522v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized wi…
6
Psychometric Comparability of LLM-Based Digital Twins
研究LLM数字孪生在心理测量上的可比性，为AI人格模拟提供科学评估框架
arXiv:2601.14264v2 Announce Type: replace-cross Abstract: Large language models (LLMs) act as digital twins for human respondents, yet their psychomet…
7
Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior
LLM心理测量评估新视角：揭示自我报告预测行为的条件与原因，为模型行为理解提供理论支撑。
arXiv:2606.12730v1 Announce Type: new Abstract: Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployme…
8
An LLM-Native Psychometric Instrument Does Not Predict LLM Behavior: Evidence Across 25 Models
LLM自述心理特质与实际行为大相径庭，25个模型验证存在“言行不一”的自我报告-行为鸿沟。
arXiv:2606.09843v1 Announce Type: cross Abstract: Large language models (LLMs) produce stable self-reports on personality inventories, but these self-…
9
GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing
用生成式投射测试替代自我报告，让LLM心理测量更可靠，摆脱语料污染与方向性偏差
arXiv:2606.00860v1 Announce Type: cross Abstract: Self-report questionnaires remain the prevailing tool for probing the psychological states of person…
10
Human Psychometric Questionnaires Mischaracterize LLM Behavior
人类心理问卷真的能测准大模型行为？这项研究用八个开源模型揭开了方法论缺陷。
arXiv:2509.10078v4 Announce Type: replace-cross Abstract: We examine whether human psychometric questionnaires can serve as reliable tools for charact…
11
Psychometric Item Validation Using Virtual Respondents with Trait-Response Mediators
用虚拟受访者进行心理测量项目验证，特质-响应中介模型带来全新范式
arXiv:2507.05890v4 Announce Type: replace-cross Abstract: As psychometric surveys are increasingly used to assess the traits of large language models …
12
Can We Trust AI-Inferred User States. A Psychometric Framework for Validating the Reliability of Users States Classification by LLMs in Operational Environments
LLM推断的用户状态能信吗？本文提出心理测量框架验证其可靠性。
arXiv:2605.15734v1 Announce Type: new Abstract: The use of large language models to assess user states in conversational and adaptive systems is based…