Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913170647416832 |
|---|---|
| author | Yehudai, Asaf Rozen, Naama Gera, Ariel |
| author_facet | Yehudai, Asaf Rozen, Naama Gera, Ariel |
| contents | Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; however, it remains unclear whether they can manifest behavior that adheres to a coherent, human-like value structure. In this work, we draw on established psychological value theory to induce human-like values in LLMs and assess their alignment with patterns observed in human studies. Using validated psychological questionnaires, we conduct large-scale experiments -- over 5 million questions -- to evaluate value structures and value-behavior relationships in leading LLMs and compare them to humans. Our findings reveal strong agreement between value-prompted LLMs and humans across both dimensions. Moreover, incorporating human value distributions enhances population-level simulations with value-induced LLMs. These findings highlight the potential of value-induced LLMs as effective, psychologically grounded tools for simulating human behavior. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_30036 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Teaching Values to Machines: Simulating Human-Like Behavior in LLMs Yehudai, Asaf Rozen, Naama Gera, Ariel Artificial Intelligence Computation and Language Large Language Models (LLMs) demonstrate a remarkable capacity to adopt different personas and roles; however, it remains unclear whether they can manifest behavior that adheres to a coherent, human-like value structure. In this work, we draw on established psychological value theory to induce human-like values in LLMs and assess their alignment with patterns observed in human studies. Using validated psychological questionnaires, we conduct large-scale experiments -- over 5 million questions -- to evaluate value structures and value-behavior relationships in leading LLMs and compare them to humans. Our findings reveal strong agreement between value-prompted LLMs and humans across both dimensions. Moreover, incorporating human value distributions enhances population-level simulations with value-induced LLMs. These findings highlight the potential of value-induced LLMs as effective, psychologically grounded tools for simulating human behavior. |
| title | Teaching Values to Machines: Simulating Human-Like Behavior in LLMs |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2605.30036 |