When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs

A new arXiv study (2608.25977v1) finds that the personality of large language models (LLMs) is not static but emerges layer-by-layer and is sensitive to quantization, prompting, and decoding. Testing open-source LLMs across 4-bit (GPTQ, AWQ) and 2-bit (AQLM) precisions, the researchers found ENFJ remains dominant across models and precisions, 4-bit quantization preserves coarse personality structure while 2-bit disrupts consistency, and personality decisions emerge in upper layers. The study introduces Uncertainty-Amplified Layer Decoding (UALD) to analyze decoding-induced personality drift, highlighting implications for personality-sensitive chatbot applications.

arXiv:2608.25977v1 Announce Type: new Abstract: 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 4-bit methods GPTQ, AWQ and extreme 2-bit settings AQLM variants . Beyond output-level evaluation, we examine how personality emerges across layers through option-level entropy and confidence-gap dynamics, and introduce Uncertainty-Amplified Layer Decoding UALD to study decoding-induced personality drift at inference time. Our results reveal a key insight: LLMs' personality is not a static property, but an emergent, layer-dependent decision process sensitive to quantization, prompting, and decoding. Specifically, we find that 1 ENFJ remains dominant across model families and precisions; 2 4-bit quantization largely preserves coarse personality structure, while 2-bit quantization disrupts fine-grained prompt consistency and cross-precision agreement; 3 personality decisions emerges in upper layers, following substantial ambiguity in early layers; and 4 inference decoding can shift personality, while personality-aligned conditioning improves robustness. These findings provide a new perspective on the behavioral reliability of quantized LLMs and highlight the importance of considering internal dynamics and inference strategies in personality-sensitive chatbot applications.