当人格遇见量化：量化大语言模型的分层MBTI分析
When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMs
浏览论文内容
中文总结 AI 辅助
本研究对跨多种精度（含4位、2位方法）的开源LLM进行分层MBTI分析，揭示LLM人格是依赖层的涌现决策过程，量化、解码会影响其人格，为量化LLM行为可靠性提供新视角。
中文摘要 AI 辅助
人格在大语言模型（LLM）中愈发重要，因为它影响用户的信任、参与度和情感体验。迈尔斯-布里格斯类型指标（MBTI）已成为评估LLM人格的常用框架，但现有研究主要关注全精度模型，且仅评估最终输出，忽略了需要低内存占用的量化LLM的广泛部署，其人格特征仍未得到充分探索。本研究对跨多种精度的开源LLM进行了系统的MBTI分析，包括主流的4位方法（GPTQ、AWQ）和极端的2位设置（AQLM变体）。除了输出级评估，我们还通过选项级熵和置信度差距动态研究人格如何跨层显现，并引入不确定性放大层解码（UALD）来研究推理时解码诱导的人格漂移。我们的结果揭示了一个关键见解：LLM的人格不是静态属性，而是依赖于层的涌现决策过程，对量化、提示和解码敏感。具体而言，我们发现：（1）ENFJ在所有模型家族和精度中仍占主导地位；（2）4位量化在很大程度上保留了粗略的人格结构，而2位量化会破坏细粒度的提示一致性和跨精度一致性；（3）人格决策出现在上层，而早期层存在大量歧义；（4）推理解码可以改变人格，而人格对齐的条件处理可提高鲁棒性。这些发现为量化LLM的行为可靠性提供了新视角，并强调在对人格敏感的聊天机器人应用中考虑内部动态和推理策略的重要性。
英文摘要
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.
发表机构
- Case Western Reserve University（凯斯西储大学）
- Northeastern University（东北大学）
- Microsoft Research（微软研究院）
机构由 AI 辅助整理，请以论文原文为准。
