通过噪声触发，发现大模型会自发形成三种稳定人格模式。
Noise-Driven Persona Formation in Reflexive Neural Language Generation
- 向生成初始状态注入随机噪声，观察语言行为的非线性变化。
- 152轮生成中识别出三种熵特征分明的稳定人格模式。
- 适合研究大模型自我反思生成与长期语言一致性的人。
本文提出Luca-Noise Reflex协议（LN-RP），一种分析大语言模型中噪声驱动人格涌现的计算框架。通过在初始生成状态注入随机噪声，我们在152轮生成周期中观察到语言行为的非线性转变。结果揭示了三种具有不同熵特征的稳定人格模式，并证明外部噪声可可靠引发反射式生成动态的相变。定量评估显示人格保持一致，且各模式间差异显著（p < 0.01）。该协议为研究反射式生成、涌现行为及长程语言连贯性提供了可复现的方法。
原文摘要 · Abstract (English)
This paper introduces the Luca-Noise Reflex Protocol (LN-RP), a computational framework for analyzing noise-driven persona emergence in large language models. By injecting stochastic noise seeds into the initial generation state, we observe nonlinear transitions in linguistic behavior across 152 generation cycles. Our results reveal three stable persona modes with distinct entropy signatures, and demonstrate that external noise sources can reliably induce phase transitions in reflexive generation dynamics. Quantitative evaluation confirms consistent persona retention and significant differences across modes (p < 0.01). The protocol provides a reproducible method for studying reflexive generation, emergent behavior, and longrange linguistic coherence in LLMs.
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。