发表机构
Southern Methodist University; Washington University in St. Louis（南卫理公会大学; 圣路易斯华盛顿大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究旨在从文本中准确评估人格，提出微调多智能体框架，通过掩码语言建模和心理测量监督让子智能体针对特质采用不同视角，评判大语言模型生成预测，经实验验证该方法可扩展且可解释，突出多智能体推理优势。
AI 中文摘要
从文本中准确评估人格具有挑战性，因为特质是潜在的、依赖上下文的，且在长叙事中往往表达得很微妙。大语言模型通过处理广泛文本上下文提供了新机会，但预训练可能会引发潜在的“人格类”偏差，导致单模型推理不一致。我们提出一种用于检测大五人格特质的微调多智能体框架，其中子智能体通过掩码语言建模和心理测量监督，针对每个特质采用高、低或中性视角。一个评判大语言模型聚合并比较子智能体输出以生成最终特质预测，捕捉多个互补视角并减轻个体模型偏差。我们通过定量和定性实验在生活叙事数据集上评估该框架，包括基线、消融和推理质量分析。我们的方法为基于文本的人格推理提供了一种可扩展且可解释的方法，突出了基于心理测量监督的多智能体推理的好处。
英文摘要
Accurately assessing personality from text is challenging because traits are latent, context-dependent, and often subtly expressed across long narratives. Large language models (LLMs) offer new opportunities by processing extensive textual contexts, but pretraining of these models can induce latent "personality-like" biases, making single-model inferences inconsistent. We propose a fine-tuned multi-agent framework for detecting OCEAN personality traits, in which sub-agents are conditioned to adopt high, low, or neutral perspectives for each trait through masked language modeling (MLM) and psychometric supervision. A judge LLM aggregates and compares sub-agent outputs to generate final trait predictions, capturing multiple complementary perspectives while mitigating individual model biases. We evaluate the framework on life narrative dataset through quantitative and qualitative experiments, including baselines, ablations, and inference quality analyses. Our approach offers a scalable and interpretable method for text-based personality inference, highlighting the benefits of multi-agent reasoning grounded in psychometric supervision.
