arXiv 2604.110482026-05-12cs.CLcs.AI

对人格引导对大语言模型能力影响的系统分析

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

School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China（东北大学计算机科学与工程学院，沈阳 110819，中国）；School of Computing and Information Systems, Singapore Management University, Singapore 178902, Singapore（新加坡管理大学计算机与信息系统学院，新加坡 178902，新加坡）；School of Computer and Communication Engineering, Northeastern University, Qinhuangdao 066004, China（东北大学计算机与通信工程学院，秦皇岛 066004，中国）

Jiaqi Chen, Ming Wang, Tingna Xie, Shi Feng, Yongkang Liu

发表信息：: Chen, J., Wang, M., Xie, T., Feng, S., & Liu, Y. (2026). A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities. Proceedings of the Annual Meeting of the Cognitive Science Society, 48

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文通过NPTI框架诱导大模型五种人格特质，发现人格引导对认知任务性能有稳定影响，且不同特质对任务表现有不同影响，提出动态人格路由策略提升性能。

摘要：

向大型语言模型（LLMs）注入特定人格特征是定制交互风格的常见做法，但其对底层认知能力的影响尚不清楚。我们采用基于神经元的人格特质诱导（NPTI）框架，在LLMs中诱导大五人格特质，并在六个认知基准测试中评估性能。我们的发现表明，人格诱导在表层风格变化之外，产生了稳定且可重复的认知任务性能变化。这些影响具有强任务依赖性：某些人格在指令遵循上产生一致提升，而其他人格则损害复杂推理。效应大小系统性地由特质维度变化，其中开放性和外向性影响最显著。此外，LLM效应与人类人格-认知关系显示出73.68%的方向一致性。基于这些规律，我们提出动态人格路由（DPR），一种轻量级的查询适应策略，在不额外训练的情况下优于最佳静态人格。

英文摘要：

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.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。