When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs
Personality is increasingly important in large language models (LLMs), as it shapes users' trust, engagement, and emotional experiences. While the Myers--Briggs Type Indicator (MBTI) has emerged as a common framework for assessing LLMs' personality, existing studies focus primarily on full-precision models and evaluate only final outputs. They overlook the widespread deployment of quantized LLMs requiring low memory footprints, whose personality traits remain underexplored. In this work, we present a systematic MBTI analysis of open-source LLMs across multiple precisions, including mainstream
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 54%An interviewer–evaluator–judger LLM framework for text-based personality inference - Nature →
- PossiblePossibly related (embedding) · 50%Examining Human-Like Behaviors in LLMs: A Multi-Dimensional Analysis of Model Behaviors, User Factors, and System Prompts - Apple Machine Learning Research →
- LinkedLinked via arxiv author · 85%Yao Fu →
“When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs”
- LinkedLinked via arxiv author · 85%Lijia Huang →
“When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs”
- LinkedLinked via arxiv author · 85%Xiaomin Li →
“When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs”
- LinkedLinked via arxiv author · 85%Runchao Li →
“When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs”
- LinkedLinked via arxiv author · 85%Qingyu Yin →
“When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs”
- LinkedLinked via arxiv author · 85%Kenneth A. Loparo →
“When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs”