About this document

MBTI Personality Inference with LLMs by NEMESIS GAMING is a document available to read on EtoBox.

This thesis presents MBTI-RAG, a novel framework that utilizes large language models (LLMs) for automatic personality detection, specifically focusing on the Myers-Briggs Type Indicator (MBTI). It addresses challenges such as class imbalance, interpretability, and hallucinated predictions by employing data augmentation, contrastive embedding learning, and retrieval-augmented generation. Experimental results demonstrate that MBTI-RAG significantly outperforms existing models, providing transparent and psycho

Author

NEMESIS GAMING

Language

EN