Research
A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities
arXiv:2604.11048v1 Announce Type: cross Abstract: Imbuing Large Language Models (LLMs) with specific personas is prevalent for tailoring interaction styles, yet the impact on underlying cognitive capa
arXiv:2604.11048v1 Announce Type: cross Abstract: 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.
Related
- TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning
- GRACE: A Dynamic Coreset Selection Framework for Large Language Model Optimization
- Scientific Knowledge-driven Decoding Constraints Improving the Reliability of LLMs
- AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought
Source: arXiv cs.AI | 2026-04-14