人格推理中的认知对齐：利用原型理论进行MBTI推断
Cognitive Alignment in Personality Reasoning: Leveraging Prototype Theory for MBTI Inference
AI总结：
ProtoMBTI通过原型理论与认知对齐，提升文本人格推断的准确性和泛化能力。
摘要：
从文本中识别人格通常被设定为硬标签分类，这掩盖了人类人格判断的渐进、原型性质。我们提出了ProtoMBTI，一种与认知对齐的MBTI推断框架，该框架在基于LLM的流程中将原型理论加以实施。首先，我们通过LLM引导的多维增强（语义、语言、情感）构建了一个平衡、质量可控的语料库。接着，我们使用LoRA微调一个轻量级（<=2B）编码器，以学习判别嵌入并标准化一组人格原型。在推断过程中，我们为查询帖子检索前k个原型，并执行检索-重用-修订-保留循环：模型通过基于提示的投票聚合原型证据，当出现不一致时进行修订，并在正确预测时保留样本以持续丰富原型库。在Kaggle和Pandora基准测试中，ProtoMBTI在四个MBTI二元分类和完整的16种类型任务上均优于基线，且表现出稳健的跨数据集泛化能力。我们的结果表明，将推断过程与心理原型推理对齐，在文本基于的人格建模中带来了准确率、可解释性和迁移性的提升。
英文摘要：
Personality recognition from text is typically cast as hard-label classification, which obscures the graded, prototype-like nature of human personality judgments. We present ProtoMBTI, a cognitively aligned framework for MBTI inference that operationalizes prototype theory within an LLM-based pipeline. First, we construct a balanced, quality-controlled corpus via LLM-guided multi-dimensional augmentation (semantic, linguistic, sentiment). Next, we LoRA-fine-tune a lightweight (<=2B) encoder to learn discriminative embeddings and to standardize a bank of personality prototypes. At inference, we retrieve top-k prototypes for a query post and perform a retrieve--reuse--revise--retain cycle: the model aggregates prototype evidence via prompt-based voting, revises when inconsistencies arise, and, upon correct prediction, retains the sample to continually enrich the prototype library. Across Kaggle and Pandora benchmarks, ProtoMBTI improves over baselines on both the four MBTI dichotomies and the full 16-type task, and exhibits robust cross-dataset generalization. Our results indicate that aligning the inference process with psychological prototype reasoning yields gains in accuracy, interpretability, and transfer for text-based personality modeling.
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。
