用原型理论提升文本人格判断，让AI更像人一样思考
Cognitive Alignment in Personality Reasoning: Leveraging Prototype Theory for MBTI Inference
- 基于心理原型理论构建性格判断框架，模拟人类认知方式
- 在两个数据集上均优于基线，16型分类准确率显著提升
- 适合对可解释性与泛化能力有要求的性格分析研究
从文本中识别人格通常被当作硬标签分类任务，忽略了人类性格判断的渐进性和原型特征。我们提出ProtoMBTI，一个与认知对齐的MBTI推断框架，将原型理论融入基于大模型的流程。首先，通过大模型引导的多维增强（语义、语言、情感）构建平衡且高质量的语料库；其次，对轻量级（≤2B）编码器进行LoRA微调，学习判别性嵌入并标准化人格原型库；推理时，对查询文本检索前k个原型，执行“检索-复用-修正-保留”循环：模型通过提示投票聚合原型证据，在不一致时修正，并在预测正确后将样本保留在原型库中持续丰富。在Kaggle和Pandora基准上，ProtoMBTI在四个MBTI二分维度及完整16型任务中均优于基线，展现出强跨数据集泛化能力。结果表明，将推理过程与心理学原型推理对齐，能提升文本人格建模的准确性、可解释性与迁移性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。