研究大模型如何在内部表示不同人格特征，发现人格编码集中在最后三分之一层。
Localizing Persona Representations in LLMs
- 通过降维与模式识别定位人格信息主要编码在模型最后三分之一层。
- 伦理观如相对主义与功利主义激活重叠，政治立场如保守与自由则分布更分散。
- 揭示了人格特征在模型中的可解释性，适合研究模型内表示机制的学者。
我们研究了大型语言模型（LLMs）中人格特征——即人类特质、价值观和信念的独特集合——在表示空间中的编码方式。利用多种降维与模式识别方法，我们首先识别出表现出最大差异的模型层。随后分析选定层内的激活情况，探究特定人格相对于其他人格的编码方式，包括共享与独立的嵌入空间。结果表明，在多个预训练的解码器仅用型LLM中，所分析的人格特征仅在解码器层的最后三分之一部分显示出显著的表示差异。我们观察到特定伦理观点（如道德虚无主义与功利主义）存在激活重叠，暗示一定程度的多义性；相比之下，保守主义与自由主义等政治意识形态则表现为更明确的区域分化。这些发现有助于深化对大模型内部表征的理解，并为未来调节模型输出中特定人类特质提供依据。警告：本文包含可能令人不适的示例语句。
原文摘要 · Abstract (English)
We present a study on how and where personas -- defined by distinct sets of human characteristics, values, and beliefs -- are encoded in the representation space of large language models (LLMs). Using a range of dimension reduction and pattern recognition methods, we first identify the model layers that show the greatest divergence in encoding these representations. We then analyze the activations within a selected layer to examine how specific personas are encoded relative to others, including their shared and distinct embedding spaces. We find that, across multiple pre-trained decoder-only LLMs, the analyzed personas show large differences in representation space only within the final third of the decoder layers. We observe overlapping activations for specific ethical perspectives -- such as moral nihilism and utilitarianism -- suggesting a degree of polysemy. In contrast, political ideologies like conservatism and liberalism appear to be represented in more distinct regions. These findings help to improve our understanding of how LLMs internally represent information and can inform future efforts in refining the modulation of specific human traits in LLM outputs. Warning: This paper includes potentially offensive sample statements.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。