The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Models

• URL: http://arxiv.org/abs/2512.07092v1
• Date: Mon, 08 Dec 2025 02:00:57 GMT
• Title: The Geometry of Persona: Disentangling Personality from Reasoning in Large Language Models
• Authors: Zhixiang Wang,
• Abstract summary: We propose the Soul Engine, a framework based on the Linear Representation Hypothesis.<n>Using a dual-head architecture on a frozen Qwen-2.5 base, we extract disentangled personality vectors.<n>The model achieves a Mean Squared Error (MSE) of 0.011 against psychological ground truth.
• Score: 6.115372688029641
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• PERSONA: Dynamic and Compositional Inference-Time Personality Control via Activation Vector Algebra [84.59328460968872]
  Current methods for personality control in Large Language Models rely on static prompting or expensive fine-tuning.<n>We introduce PERSONA, a training-free framework that achieves fine-tuning level performance through direct manipulation of personality vectors.<n>On PersonalityBench, our approach achieves a mean score of 9.60, nearly matching the supervised fine-tuning upper bound of 9.61 without any gradient updates.
  arXiv  Detail & Related papers  (2026-02-17T15:47:58Z)
• Geometry-Aware Decoding with Wasserstein-Regularized Truncation and Mass Penalties for Large Language Models [9.059725329168435]
  Top-W is a geometry-aware truncation rule that uses Wasserstein distance-defined over token-embedding geometry.<n>We show that Top-W consistently outperforms prior state-of-the-art decoding approaches achieving up to 33.7% improvement.
  arXiv  Detail & Related papers  (2026-02-10T22:36:48Z)
• Attention Is Not What You Need [0.0]
  We argue that standard multi-head attention is best seen as a form of tensor lifting.<n>We propose an attention-free architecture based on Grassmann flows.
  arXiv  Detail & Related papers  (2025-12-22T14:29:18Z)
• Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model [32.831576387973875]
  We propose a two-stage deterministic framework for stable, accurate and fine-grained geometric dense prediction.<n>Specifically, in the first stage, the core predictor employs a single-step deterministic formulation with a clean-data objective.<n>In the second stage, the detail sharpener performs a constrained multi-step rectified-flow refinement within the manifold defined by the core predictor.
  arXiv  Detail & Related papers  (2025-11-30T18:57:25Z)
• The Alignment Game: A Theory of Long-Horizon Alignment Through Recursive Curation [13.835275211048113]
  We model alignment as an interaction between two factions: the Model Owner, who filters which outputs should be learned by the model, and the Public User, who determines which outputs are ultimately shared and retained through interactions with the model.<n>Our analysis reveals three structural convergence regimes depending on the degree of preference alignment: consensus collapse, compromise on shared optima, and asymmetric refinement.<n>We show that alignment is not a static goal but an evolving equilibrium, shaped both by power asymmetries and path dependence.
  arXiv  Detail & Related papers  (2025-11-16T22:17:16Z)
• Beyond 'Aha!': Toward Systematic Meta-Abilities Alignment in Large Reasoning Models [86.88657425848547]
  Large reasoning models (LRMs) already possess a latent capacity for long chain-of-thought reasoning.<n>We explicitly align models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks.<n>Our three stage-pipeline individual alignment, parameter-space merging, and domain-specific reinforcement learning, boosts performance by over 10% relative to instruction-tuned baselines.
  arXiv  Detail & Related papers  (2025-05-15T17:58:33Z)
• RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets [44.655049022141384]
  We present RigAnything, a novel autoregressive transformer-based model.<n>It makes 3D assets rig-ready by probabilistically generating joints and skeleton topologies and assigning skinning weights in a template-free manner.<n>It demonstrates state-of-the-art performance across diverse object types, including humanoids, quadrupeds, marine creatures, insects, and many more.
  arXiv  Detail & Related papers  (2025-02-13T18:59:13Z)
• Identifiable Representation and Model Learning for Latent Dynamic Systems [0.0]
  We study the problem of identifiable representation and model learning for latent dynamic systems.<n>We prove that, for linear and affine nonlinear latent dynamic systems with sparse input matrices, it is possible to identify the latent variables up to scaling.
  arXiv  Detail & Related papers  (2024-10-23T13:55:42Z)
• Learning Physical Dynamics with Subequivariant Graph Neural Networks [99.41677381754678]
  Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. Physical laws abide by symmetry, which is a vital inductive bias accounting for model generalization. Our model achieves on average over 3% enhancement in contact prediction accuracy across 8 scenarios on Physion and 2X lower rollout MSE on RigidFall.
  arXiv  Detail & Related papers  (2022-10-13T10:00:30Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes [117.76767853430243]
  We introduce SNARF, which combines the advantages of linear blend skinning for polygonal meshes with neural implicit surfaces. We propose a forward skinning model that finds all canonical correspondences of any deformed point using iterative root finding. Compared to state-of-the-art neural implicit representations, our approach generalizes better to unseen poses while preserving accuracy.
  arXiv  Detail & Related papers  (2021-04-08T17:54:59Z)
• Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation [75.59415852802958]
  Shape-My-Face (SMF) is a powerful encoder-decoder architecture based on an improved point cloud encoder, a novel visual attention mechanism, graph convolutional decoders with skip connections, and a specialized mouth model. Our model provides topologically-sound meshes with minimal supervision, offers faster training time, has orders of magnitude fewer trainable parameters, is more robust to noise, and can generalize to previously unseen datasets.
  arXiv  Detail & Related papers  (2020-12-16T20:02:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.