Cognitive Alignment in Personality Reasoning: Leveraging Prototype Theory for MBTI Inference

TL;DR

This paper introduces ProtoMBTI, a cognitively inspired framework that uses prototype theory and large language models to improve personality inference from text, achieving better accuracy and interpretability.

Contribution

The paper presents a novel prototype-based approach for MBTI inference that aligns with psychological theories and enhances performance and generalization.

Findings

ProtoMBTI outperforms baseline models on Kaggle and Pandora benchmarks.

The framework improves accuracy on both MBTI dichotomies and full 16-type classification.

ProtoMBTI demonstrates robust cross-dataset generalization.

Abstract

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.