从五维到更多：大型语言模型作为精确且可解释的心理档案师
From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers
AI总结：
本文研究了大型语言模型能否通过少量量化输入建模人类心理特质的相关结构，发现其在零样本情况下能准确预测心理特质，揭示了LLM通过抽象和推理实现精确预测的机制。
摘要：
个体内的心理构念普遍被认为相互关联。我们研究了大型语言模型（LLMs）能否通过最小的量化输入建模人类心理特质的相关结构。我们促使各种LLMs使用816名人类个体的Big Five人格特质评分来扮演其对九种其他心理量表的回应。LLMs在捕捉人类心理结构方面表现出显著的准确性，LLM生成的跨量表相关性模式与人类数据的相关性（R²>0.89）高度一致。这种零样本性能远超基于语义相似性的预测，接近直接在数据集上训练的机器学习算法的准确性。对推理痕迹的分析显示，LLMs采用一种系统性的两阶段过程：首先，它们将原始Big Five响应转换为自然语言的人格摘要，通过信息选择和压缩，类似于生成足够的统计信息。其次，它们基于这些摘要进行推理，生成目标量表的响应。在信息选择方面，LLMs识别出与训练算法相同的键人格因素，尽管它们无法区分因素内的项目重要性。所得到的压缩摘要不仅仅是冗余的表示，而是捕捉了协同信息——将它们添加到原始分数中可以增强预测的一致性，这表明它们编码了特质相互作用的新兴、二级模式。我们的发现表明，LLMs可以通过抽象和推理的过程，从最小的数据中精确预测个体参与者的心理特质，为心理模拟提供了强大的工具，并提供了关于其新兴推理能力的有价值的见解。
英文摘要：
Psychological constructs within individuals are widely believed to be interconnected. We investigated whether and how Large Language Models (LLMs) can model the correlational structure of human psychological traits from minimal quantitative inputs. We prompted various LLMs with Big Five Personality Scale responses from 816 human individuals to role-play their responses on nine other psychological scales. LLMs demonstrated remarkable accuracy in capturing human psychological structure, with the inter-scale correlation patterns from LLM-generated responses strongly aligning with those from human data $(R^2 > 0.89)$. This zero-shot performance substantially exceeded predictions based on semantic similarity and approached the accuracy of machine learning algorithms trained directly on the dataset. Analysis of reasoning traces revealed that LLMs use a systematic two-stage process: First, they transform raw Big Five responses into natural language personality summaries through information selection and compression, analogous to generating sufficient statistics. Second, they generate target scale responses based on reasoning from these summaries. For information selection, LLMs identify the same key personality factors as trained algorithms, though they fail to differentiate item importance within factors. The resulting compressed summaries are not merely redundant representations but capture synergistic information--adding them to original scores enhances prediction alignment, suggesting they encode emergent, second-order patterns of trait interplay. Our findings demonstrate that LLMs can precisely predict individual participants' psychological traits from minimal data through a process of abstraction and reasoning, offering both a powerful tool for psychological simulation and valuable insights into their emergent reasoning capabilities.
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。
