# Linear Personality Probing and Steering in LLMs: A Big Five Study

arXiv: https://arxiv.org/abs/2512.17639 · HTML: https://mlsanity.com/paper/2512.17639/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 64 references that are in the map.
- First posted on arXiv 19 Dec 2025.

## Builds on (most cited first, 9 of 9)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models](https://mlsanity.com/paper/2403.19647/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Toward universal steering and monitoring of AI models](https://mlsanity.com/paper/2502.03708/) (2025)
- [Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering](https://mlsanity.com/paper/2412.10427/) (2024)

## Built on by (most cited first, 9 of 9)

- [Curveball Steering: The Right Direction To Steer Isn't Always Linear](https://mlsanity.com/paper/2603.09313/) (2026)
- [Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention](https://mlsanity.com/paper/2605.05892/) (2026)
- [Controllable and explainable personality sliders for LLMs at inference time](https://mlsanity.com/paper/2603.03326/) (2026)
- [Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation](https://mlsanity.com/paper/2603.18893/) (2026)
- [Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs](https://mlsanity.com/paper/2604.11120/) (2026)
- [Neuroscience-Inspired Analyses of Visual Interestingness in Multimodal Transformers](https://mlsanity.com/paper/2605.08188/) (2026)
- [Personality, Role, and Expressive Style in Large Language Models: An Interactionist Analysis](https://mlsanity.com/paper/2605.28037/) (2026)
- [The Geometry of Personality: Activation Steering with Jungian Cognitive Functions](https://mlsanity.com/paper/2607.20803/) (2026)
- [Emotional Labor Strategy Preferences in LLM Personas](https://mlsanity.com/paper/2609.00310/) (2026)

## Abstract (arXiv)

Large language models (LLMs) exhibit distinct and consistent personalities that greatly impact trust and engagement. While this means that personality frameworks would be highly valuable tools to characterize and control LLMs' behavior, current approaches remain either costly (post-training) or brittle (prompt engineering). Probing and steering via linear directions has recently emerged as a cheap and efficient alternative. In this paper, we investigate whether linear directions aligned with the Big Five personality traits can be used for probing and steering model behavior. Using Llama 3.3 70B, we generate descriptions of 406 fictional characters and their Big Five trait scores. We then prompt the model with these descriptions and questions from the Alpaca questionnaire, allowing us to sample hidden activations that vary along personality traits in known, quantifiable ways. Using linear regression, we learn a set of per-layer directions in activation space, and test their effectiveness for probing and steering model behavior. Our results suggest that linear directions aligned with trait-scores are effective probes for personality detection, while their steering capabilities strongly depend on context, producing reliable effects in forced-choice tasks but limited influence in open-ended generation or when additional context is present in the prompt.