When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs
Provides technical insights into how quantization affects behavioral reliability of LLMs through internal layer dynamics, relevant for model deployment.
AI Summary
Researchers conducted a layer-wise MBTI personality analysis of quantized LLMs, finding personality is emergent and -sensitive rather than static.
Excerpt
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 pres