Guardado en:
| Autores principales: | , |
|---|---|
| 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 |