Persona Without Substrate: Regime-Dependence and the LLM Individuation Problem

无基质人格：机制依赖性与大语言模型（LLM）的个体化问题

Abstract: Beckmann & Butlin’s (2026) ontological framework for the LLM individuation problem inherits an unargued cross-regime co-reference assumption from the persona-vectors literature: that the same direction picks out the same content under prompt-conditioning, gradient-descent fine-tuning, and inference-time steering.

摘要： Beckmann 和 Butlin (2026) 针对大语言模型（LLM）个体化问题提出的本体论框架，继承了人格向量文献中一个未经论证的“跨机制共指假设”：即在提示词调节（prompt-conditioning）、梯度下降微调（gradient-descent fine-tuning）以及推理时引导（inference-time steering）下，同一个方向指向的是相同的内容。

We present four empirical wedges from persona-topology experiments on Qwen3-4B-Instruct and Mistral-7B-Instruct-v0.2 - non-collinearity of prompt-extracted vectors and fine-tune basins; fictional personas displacing the model along real-anchor directions more strongly than real anchors do; contradictory-valenced mixtures biased toward a training-history-determined attractor; and asymmetric compositional algebra under inference-time arithmetic versus fine-tune-time chimera training - that jointly undermine the assumption.

我们通过对 Qwen3-4B-Instruct 和 Mistral-7B-Instruct-v0.2 进行人格拓扑实验，提出了四个经验性证据（楔子），共同削弱了上述假设：提示词提取向量与微调盆地（fine-tune basins）之间的非共线性；虚构人格在真实锚点方向上对模型的位移作用强于真实锚点本身；具有矛盾效价的混合体偏向于由训练历史决定的吸引子；以及推理时算术运算与微调时“嵌合体训练”（chimera training）之间不对称的组合代数。

We propose regime-indexed individuation: the identity unit for representational content is a (vehicle, regime) pair, not a vehicle alone. Under this framework, Beckmann & Butlin’s three candidate positions describe three different regime-internal objects rather than competing for the same referent; the same diagnosis applies to Mollo & Millière, Chalmers, and Cerullo.

我们提出了“机制索引个体化”（regime-indexed individuation）的概念：表征内容的同一性单位是一个（载体，机制）对，而非单一的载体。在该框架下，Beckmann 和 Butlin 提出的三个候选立场描述的是三种不同的机制内部对象，而非竞争同一个指称对象；同样的诊断也适用于 Mollo & Millière、Chalmers 以及 Cerullo 的观点。