The Need for a Socially-Grounded Persona Framework for User Simulation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918303452102656 |
|---|---|
| author | Venkit, Pranav Narayanan Li, Yu Pruksachatkun, Yada Wu, Chien-Sheng |
| author_facet | Venkit, Pranav Narayanan Li, Yu Pruksachatkun, Yada Wu, Chien-Sheng |
| contents | Synthetic personas are widely used to condition large language models (LLMs) for social simulation, yet most personas are still constructed from coarse sociodemographic attributes or summaries. We revisit persona creation by introducing SCOPE, a socially grounded framework for persona construction and evaluation, built from a 141-item, two-hour sociopsychological protocol collected from 124 U.S.-based participants. Across seven models, we find that demographic-only personas are a structural bottleneck: demographics explain only ~1.5% of variance in human response similarity. Adding sociopsychological facets improves behavioral prediction and reduces over-accentuation, and non-demographic personas based on values and identity achieve strong alignment with substantially lower bias. These trends generalize to SimBench (441 aligned questions), where SCOPE personas outperform default prompting and NVIDIA Nemotron personas, and SCOPE augmentation improves Nemotron-based personas. Our results indicate that persona quality depends on sociopsychological structure rather than demographic templates or summaries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07110 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The Need for a Socially-Grounded Persona Framework for User Simulation Venkit, Pranav Narayanan Li, Yu Pruksachatkun, Yada Wu, Chien-Sheng Computation and Language Artificial Intelligence Computers and Society Synthetic personas are widely used to condition large language models (LLMs) for social simulation, yet most personas are still constructed from coarse sociodemographic attributes or summaries. We revisit persona creation by introducing SCOPE, a socially grounded framework for persona construction and evaluation, built from a 141-item, two-hour sociopsychological protocol collected from 124 U.S.-based participants. Across seven models, we find that demographic-only personas are a structural bottleneck: demographics explain only ~1.5% of variance in human response similarity. Adding sociopsychological facets improves behavioral prediction and reduces over-accentuation, and non-demographic personas based on values and identity achieve strong alignment with substantially lower bias. These trends generalize to SimBench (441 aligned questions), where SCOPE personas outperform default prompting and NVIDIA Nemotron personas, and SCOPE augmentation improves Nemotron-based personas. Our results indicate that persona quality depends on sociopsychological structure rather than demographic templates or summaries. |
| title | The Need for a Socially-Grounded Persona Framework for User Simulation |
| topic | Computation and Language Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2601.07110 |