Machine Mindset: An MBTI Exploration of Large Language Models

TL;DR

This paper introduces 'Machine Mindset', a novel method for embedding MBTI personality traits into large language models through a two-phase fine-tuning process, enhancing personality consistency for personalized AI.

Contribution

It develops a new training methodology and datasets for integrating MBTI traits into LLMs, enabling models to internalize and maintain stable personality profiles.

Findings

Models exhibit alignment with specified MBTI traits.

Enhanced personality consistency in LLMs demonstrated.

Open-source release of models and datasets.

Abstract

We present a novel approach for integrating Myers-Briggs Type Indicator (MBTI) personality traits into large language models (LLMs), addressing the challenges of personality consistency in personalized AI. Our method, "Machine Mindset," involves a two-phase fine-tuning and Direct Preference Optimization (DPO) to embed MBTI traits into LLMs. This approach ensures that models internalize these traits, offering a stable and consistent personality profile. We demonstrate the effectiveness of our models across various domains, showing alignment between model performance and their respective MBTI traits. The paper highlights significant contributions in the development of personality datasets and a new training methodology for personality integration in LLMs, enhancing the potential for personalized AI applications. We also open-sourced our model and part of the data at \url{https://github.com/PKU-YuanGroup/Machine-Mindset}.