人格的几何学：从推理中分离人格特征于大型语言模型
The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Models
AI总结：
本文提出Soul Engine框架，通过解耦人格特质于LLM推理，实现安全可控的人格个性化。
摘要：
背景：个性化大型语言模型（LLMs）的部署目前受到稳定性与可塑性困境的限制。现有的对齐方法，如监督微调（SFT），依赖于随机权重更新，这通常会导致一种“对齐税”——降低一般推理能力。 方法：我们提出了Soul Engine，一个基于线性表示假说的框架，该假说认为人格特质存在于正交的线性子空间中。我们引入了SoulBench，一个通过动态上下文采样构建的数据集。使用在冻结的Qwen-2.5基础模型上的双头架构，我们提取出解耦的人格向量，而无需修改基础权重。 结果：我们的实验展示了三个突破。首先，高精度剖析：模型在心理真实值上达到均方误差（MSE）为0.011。其次，几何正交性：T-SNE可视化确认人格流形是独特且连续的，允许进行“零样本人格注入”以保持原始模型智能。第三，确定性操控：我们通过向量运算实现了对行为的稳健控制，通过广泛的消融研究进行了验证。 结论：这项工作挑战了个性化所需的微调必要性。通过从概率提示转向确定性潜在干预，我们为安全、可控的人工智能个性化提供了数学严谨的基础。
英文摘要：
Background: The deployment of personalized Large Language Models (LLMs) is currently constrained by the stability-plasticity dilemma. Prevailing alignment methods, such as Supervised Fine-Tuning (SFT), rely on stochastic weight updates that often incur an "alignment tax" -- degrading general reasoning capabilities. Methods: We propose the Soul Engine, a framework based on the Linear Representation Hypothesis, which posits that personality traits exist as orthogonal linear subspaces. We introduce SoulBench, a dataset constructed via dynamic contextual sampling. Using a dual-head architecture on a frozen Qwen-2.5 base, we extract disentangled personality vectors without modifying the backbone weights. Results: Our experiments demonstrate three breakthroughs. First, High-Precision Profiling: The model achieves a Mean Squared Error (MSE) of 0.011 against psychological ground truth. Second, Geometric Orthogonality: T-SNE visualization confirms that personality manifolds are distinct and continuous, allowing for "Zero-Shot Personality Injection" that maintains original model intelligence. Third, Deterministic Steering: We achieve robust control over behavior via vector arithmetic, validated through extensive ablation studies. Conclusion: This work challenges the necessity of fine-tuning for personalization. By transitioning from probabilistic prompting to deterministic latent intervention, we provide a mathematically rigorous foundation for safe, controllable AI personalization.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
