# A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities

arXiv: https://arxiv.org/abs/2604.11048 · HTML: https://mlsanity.com/paper/2604.11048/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 13 Apr 2026.

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

- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://mlsanity.com/paper/2306.16388/) (2023)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [From Persona to Personalization: A Survey on Role-Playing Language Agents](https://mlsanity.com/paper/2404.18231/) (2024)
- [Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization](https://mlsanity.com/paper/2406.01171/) (2024)
- [Neuron-based Personality Trait Induction in Large Language Models](https://mlsanity.com/paper/2410.12327/) (2024)
- [Behavioral Bias of Vision-Language Models: A Behavioral Finance View](https://mlsanity.com/paper/2409.15256/) (2024)

## Built on by (most cited first, 5 of 5)

- [GenPT: Beyond Self-Report for Reliable LLM Psychometrics via Generative Projective Testing](https://mlsanity.com/paper/2606.00860/) (2026)
- [Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events](https://mlsanity.com/paper/2608.06485/) (2026)
- [The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models](https://mlsanity.com/paper/2605.06196/) (2026)
- [When Cosine Similarity Fails to Reflect Linearly Accessible Structure in Dialogue Models](https://mlsanity.com/paper/2609.22522/) (2026)
- [How Well Can LLMs Simulate Real Learner Evaluations of Educational Feedback?](https://mlsanity.com/paper/2609.35376/) (2026)

## Abstract (arXiv)

Imbuing Large Language Models (LLMs) with specific personas is prevalent for tailoring interaction styles, yet the impact on underlying cognitive capabilities remains unexplored. We employ the Neuron-based Personality Trait Induction (NPTI) framework to induce Big Five personality traits in LLMs and evaluate performance across six cognitive benchmarks. Our findings reveal that persona induction produces stable, reproducible shifts in cognitive task performance beyond surface-level stylistic changes. These effects exhibit strong task dependence: certain personalities yield consistent gains on instruction-following, while others impair complex reasoning. Effect magnitude varies systematically by trait dimension, with Openness and Extraversion exerting the most robust influence. Furthermore, LLM effects show 73.68% directional consistency with human personality-cognition relationships. Capitalizing on these regularities, we propose Dynamic Persona Routing (DPR), a lightweight query-adaptive strategy that outperforms the best static persona without additional training.