Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Johnathan, Zhang, Andrew
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2603.21398
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911535682551808
author Sun, Johnathan
Zhang, Andrew
author_facet Sun, Johnathan
Zhang, Andrew
contents Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic settings, constructing persona vectors for altruism, forgiveness, and expectations of others by contrastive activation addition. Evaluating on canonical games, we find that activation steering systematically shifts both quantitative strategic choices and natural-language justifications. However, we also observe that rhetoric and strategy can diverge under steering. In addition, vectors for self-behavior and expectations of others are partially distinct. Our results suggest that persona vectors offer a promising mechanistic handle on high-level traits in strategic environments.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21398
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors
Sun, Johnathan
Zhang, Andrew
Artificial Intelligence
Computer Science and Game Theory
Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic settings, constructing persona vectors for altruism, forgiveness, and expectations of others by contrastive activation addition. Evaluating on canonical games, we find that activation steering systematically shifts both quantitative strategic choices and natural-language justifications. However, we also observe that rhetoric and strategy can diverge under steering. In addition, vectors for self-behavior and expectations of others are partially distinct. Our results suggest that persona vectors offer a promising mechanistic handle on high-level traits in strategic environments.
title Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors
topic Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2603.21398