发表机构
The Chinese University of Hong Kong, Shenzhen; Central China Normal University; Shandong Science and Technology Press, Shandong Publishing Group; Bielefeld University; South China Normal University; Frankfurt Institute for Advanced Studies（香港中文大学（深圳）; 华中师范大学; 山东科学技术出版社，山东出版集团; 比勒费尔德大学; 华南师范大学; 法兰克福高等研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过跨语言心理测量学框架评估九个LLM，发现其行为特征具有模型特异性且受语言和提供者影响，联合分析响应与NA可量化部署层面的行为签名。
AI 中文摘要
大型语言模型（LLMs）日益介入人类决策与沟通，但其行为规律仍难以系统性地刻画。我们开发了一个跨语言的心理测量学画像框架，并使用七种心理测量工具评估了九个LLM，每种模型和语言（中文和英文）分别进行了五次重复施测。在预设的重试程序后仍未解决的题目被保留为NA。对评分响应和NA响应的联合分析捕捉了响应倾向及自我报告适用性的边界。LLM表现出结构化、模型特定的画像，尽管存在共享的对齐塑造模式，即更高的亲社会性和自我调节响应，以及更低的支配性、脱离参与和有害意图认可。NA响应是结构化的而非均匀分布，表明输出被视作不适用、被拒绝或无法映射到有效响应选项的情况。语言条件和提供者来源与画像配置和可回答性相关，而重复施测显示出高可重复性，并允许恢复模型身份。人类参考和提示鲁棒性分析进一步表明这些特征是上下文依赖的。心理测量学画像与可回答性的联合分析为量化部署层面的行为特征提供了一个框架。
英文摘要
Large language models (LLMs) increasingly mediate human decisions and communication, yet their behavioural regularities remain difficult to characterize systematically. We develop a cross-linguistic psychometric profiling framework and evaluate nine LLMs using seven psychological instruments, with five repeated administrations per model and language in Chinese and English. Items unresolved after a prespecified retry procedure are retained as NA. Joint analysis of scored and NA responses captures response tendencies and boundaries of self-report applicability. LLMs exhibit structured, model-specific profiles despite a shared alignment-shaped pattern of higher prosocial and self-regulatory responses and lower dominance, disengagement and harmful-intent endorsement. NA responses are structured rather than uniformly distributed, indicating where outputs are treated as inapplicable, refused or cannot be mapped to valid response options. Language condition and provider origin are associated with profile configuration and answerability, whereas repeated administrations show high reproducibility and permit recovery of model identity. Human-reference and prompt-robustness analyses further indicate that these signatures are context dependent. Joint analysis of psychometric profiling and answerability offers a framework for quantifying deployment-level behavioural signatures.
Comments22 pages, 6 figures
