Psychological Steering of Large Language Models

• URL: http://arxiv.org/abs/2604.14463v1
• Date: Wed, 15 Apr 2026 22:45:59 GMT
• Title: Psychological Steering of Large Language Models
• Abstract summary: We introduce a psychological steering framework that performs fluency-constrained sweeps in semantically unbounded units.<n>Our method derives and calibrates residual-stream injections using psychological artifacts.<n>We show that MD injections align with the Linear Representation Hypothesis and provide reliable, approximately linear control knobs for psychological steering.
• Score: 28.317905150128595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) emulate a consistent human-like behavior that can be shaped through activation-level interventions. This paradigm is converging on additive residual-stream injections, which rely on injection-strength sweeps to approximate optimal intervention settings. However, existing methods restrict the search space and sweep in uncalibrated activation-space units, potentially missing optimal intervention conditions. Thus, we introduce a psychological steering framework that performs unbounded, fluency-constrained sweeps in semantically calibrated units. Our method derives and calibrates residual-stream injections using psychological artifacts, and we use the IPIP-NEO-120, which measures the OCEAN personality model, to compare six injection methods. We find that mean-difference (MD) injections outperform Personality Prompting (P$^2$), an established baseline for OCEAN steering, in open-ended generation in 11 of 14 LLMs, with gains of 3.6\% to 16.4\%, overturning prior reports favoring prompting and positioning representation engineering as a new frontier in open-ended psychological steering. Further, we find that a hybrid of P$^2$ and MD injections outperforms both methods in 13 of 14 LLMs, with gains over P$^2$ ranging from 5.6\% to 21.9\% and from 3.3\% to 26.7\% over MD injections. Finally, we show that MD injections align with the Linear Representation Hypothesis and provide reliable, approximately linear control knobs for psychological steering. Nevertheless, they also induce OCEAN trait covariance patterns that depart from the Big Two model, suggesting a gap between learned representations and human psychology.

Related papers

• Anatomy-Change-Aware Bidirectional Selective State-Space Memory for Clinically Deployed Thoracic Radiotherapy Auto-Contouring [0.6439594960617159]
  DAMM-Net++ is a 2.5D architecture for thoracic radiotherapy auto-contouring.<n>It addresses inter-slice surface incoherence, systematic failure on small low-contrast targets, and the absence of per-case reliability signals.<n>It achieves a mean Dice of 0.955 and HD95 of 3.78 mm, with the largest gains on low-contrast organs-at-risk.
  arXiv  Detail & Related papers  (2026-09-11T11:13:06Z)
• D3Seg: Dependency-Aware Diffusion for Brain Tumor Segmentation with Missing Modalities [54.87947751720332]
  We propose a novel segmentation model D3Seg to maintain stable performance under missing-modality settings.<n>The proposed model achieves approximately 1.5-2.0% Dice improvement on enhancing tumor (ET) and around 1.0% on tumor core (TC) across multiple missing modality configurations.
  arXiv  Detail & Related papers  (2026-05-21T09:55:42Z)
• Extracting and Steering Emotion Representations in Small Language Models: A Methodological Comparison [4.358468367889626]
  Small language models (SLMs) in the 100M-10B parameter range increasingly power production systems.<n>We present the first comparative analysis of emotion vector extraction methods for SLMs.<n>Generation-based extraction produces statistically superior emotion separation.<n>We document cross-lingual emotion entanglement in Qwen, where steering activates semantically aligned Chinese tokens.
  arXiv  Detail & Related papers  (2026-04-05T11:09:27Z)
• Longitudinal Lesion Inpainting in Brain MRI via 3D Region Aware Diffusion [3.7547060531652057]
  We present a novel pseudo-3D longitudinal inpainting framework based on Denoising Diffusion Probabilistic Models (DDPM)<n>Our model significantly outperforms the leading baseline (FastSurfer-LIT) in terms of perceptual fidelity.<n>Our framework achieves an average processing time of 2.53 min per volume, representing approximately 10x speedup over the 24.30 min required by LIT.
  arXiv  Detail & Related papers  (2026-03-05T21:34:47Z)
• Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage [65.51149575007149]
  We present Fun-DDPS, a generative framework that combines function-space diffusion models with differentiable neural operator surrogates for both forward and inverse modeling.<n>Fun-DDPS produces physically consistent realizations free from the high-frequency artifacts observed in joint-state baselines.
  arXiv  Detail & Related papers  (2026-02-12T18:58:12Z)
• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• DiffusionNFT: Online Diffusion Reinforcement with Forward Process [99.94852379720153]
  Diffusion Negative-aware FineTuning (DiffusionNFT) is a new online RL paradigm that optimize diffusion models directly on the forward process via flow matching.<n>DiffusionNFT is up to $25times$ more efficient than FlowGRPO in head-to-head comparisons, while being CFG-free.
  arXiv  Detail & Related papers  (2025-09-19T16:09:33Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment [46.776978552161395]
  Small language models (SLMs) offer a cost-effective alternative to large language models such as GPT-4.<n>SLMs offer a cost-effective alternative, but their limited capacity requires biomedical domain adaptation.<n>We propose a novel framework for adapting SLMs into high-performing clinical models.
  arXiv  Detail & Related papers  (2025-05-15T21:40:21Z)
• LLMs for Drug-Drug Interaction Prediction: A Comprehensive Comparison [3.2627279988912194]
  Large Language Models (LLMs) have revolutionized various domains, but their potential in pharmaceutical research remains largely unexplored.<n>This study thoroughly investigates LLMs' capabilities in predicting drug-drug interactions (DDIs)<n>We evaluated 18 different LLMs, including proprietary models (GPT-4, Claude, Gemini) and open-source variants (from 1.5B to 72B parameters)<n>Fine-tuned LLMs demonstrated superior performance, with Phi-3.5 2.7B achieving a sensitivity of 0.978 in DDI prediction, with an accuracy of 0.919 on balanced datasets.
  arXiv  Detail & Related papers  (2025-02-09T09:58:12Z)
• Diffusion Denoising Process for Perceptron Bias in Out-of-distribution Detection [67.49587673594276]
  We introduce a new perceptron bias assumption that suggests discriminator models are more sensitive to certain features of the input, leading to the overconfidence problem. We demonstrate that the diffusion denoising process (DDP) of DMs serves as a novel form of asymmetric, which is well-suited to enhance the input and mitigate the overconfidence problem. Our experiments on CIFAR10, CIFAR100, and ImageNet show that our method outperforms SOTA approaches.
  arXiv  Detail & Related papers  (2022-11-21T08:45:08Z)
• Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification [4.5206601127476445]
  We propose an end-to-end deep learning method for automated Bruch's membrane (BM) segmentation in AMD patients. An Attention U-Net is trained to output a probability density function of the BM position, while taking into account the natural curvature of the surface. Besides the surface position, the method also estimates an A-scan wise uncertainty measure of the segmentation output.
  arXiv  Detail & Related papers  (2022-10-26T15:49:07Z)
• Deep Implicit Statistical Shape Models for 3D Medical Image Delineation [47.78425002879612]
  3D delineation of anatomical structures is a cardinal goal in medical imaging analysis. Prior to deep learning, statistical shape models that imposed anatomical constraints and produced high quality surfaces were a core technology. We present deep implicit statistical shape models (DISSMs), a new approach to delineation that marries the representation power of CNNs with the robustness of SSMs.
  arXiv  Detail & Related papers  (2021-04-07T01:15:06Z)

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.