---
title: "When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.25977v1"
permalink: "https://feed.astralor.com/items/itm_49cd3c559fabf9de199f81a7"
published: "2026-08-26T16:32:50.000Z"
score: 73
channel: "ai"
tags: ["AWQ","GPTQ","MBTI","Quantization"]
---

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

## AI commentary

> This paper beautifully crosses quantization with personality psychology, reminding us that a model's character can drift after compression. For teams working on edge deployment, AI safety, and humanized products, it offers a layer-level lens on behavioral reliability.

## At a glance

This paper presents the first systematic MBTI personality analysis of open-source large language models (LLMs) across multiple quantization precisions, including mainstream 4-bit methods (GPTQ, AWQ) and extreme 2-bit settings (AQLM variants). Going beyond output-level evaluation, the authors 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. Key findings show that ENFJ remains dominant across model families and precisions; 4-bit quantization largely preserves coarse personality structure, while 2-bit quantization disrupts fine-grained consistency; personality decisions arise in upper layers after early-layer ambiguity; and inference decoding can shift personality. The work provides a new perspective on behavioral reliability of quantized LLMs and highlights the importance of internal dynamics for personality-sensitive chatbot applications.

## Key points

- ENFJ remains dominant across most model families and quantization precisions.
- 4-bit quantization largely preserves coarse personality structure, while 2-bit quantization disrupts fine-grained prompt consistency and cross-precision agreement.
- Personality decisions emerge in upper layers following substantial ambiguity in early layers.
- Inference decoding can shift personality, while personality-aligned conditioning improves robustness.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_49cd3c559fabf9de199f81a7