Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.27401 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914605467435008 |
|---|---|
| author | Anderson, Taylor Von Hoene, Sara Cinar, Orhan Yagizer Von Hoene, Emma Roess, Amira Crooks, Andrew Kavak, Hamdi |
| author_facet | Anderson, Taylor Von Hoene, Sara Cinar, Orhan Yagizer Von Hoene, Emma Roess, Amira Crooks, Andrew Kavak, Hamdi |
| contents | There is a growing interest in utilizing synthetic populations for a diverse range of applications. At the same time, we are witnessing a tremendous growth in artificial intelligence in all walks of life. This paper evaluates whether zero-shot large language model (LLM)-generated health survey data can serve as inputs to a conventional iterative proportional fitting (IPF) workflow for geographically explicit population synthesis. Using the 2023 Behavioral Risk Factor Surveillance System (BRFSS), we generate synthetic survey records for the U.S. states of Colorado and Mississippi with GPT-4.1 and Gemini-2.5-Pro. We use the generated data in an IPF-based synthesis pipeline and evaluate the resulting census tract-level synthetic populations against external benchmarks. Results show both LLMs capture several major state-level contrasts, indicating zero-shot generation produces geographically differentiated survey data. However, performance is strongly variable-dependent. Downstream effects in population synthesis are mixed, as IPF sometimes amplifies or reduces errors in the generated data. Spatial validation shows that LLM-based populations reproduce census tract-level patterns reasonably well, especially for variables that were more aligned with the ground truth data. Overall, the LLM-generated survey data shows promise as supplementary input, but not yet as a replacement for real survey data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_27401 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Using Zero-Shot LLM-Generated Survey Data for Geographically Explicit Population Synthesis Anderson, Taylor Von Hoene, Sara Cinar, Orhan Yagizer Von Hoene, Emma Roess, Amira Crooks, Andrew Kavak, Hamdi Computers and Society Artificial Intelligence There is a growing interest in utilizing synthetic populations for a diverse range of applications. At the same time, we are witnessing a tremendous growth in artificial intelligence in all walks of life. This paper evaluates whether zero-shot large language model (LLM)-generated health survey data can serve as inputs to a conventional iterative proportional fitting (IPF) workflow for geographically explicit population synthesis. Using the 2023 Behavioral Risk Factor Surveillance System (BRFSS), we generate synthetic survey records for the U.S. states of Colorado and Mississippi with GPT-4.1 and Gemini-2.5-Pro. We use the generated data in an IPF-based synthesis pipeline and evaluate the resulting census tract-level synthetic populations against external benchmarks. Results show both LLMs capture several major state-level contrasts, indicating zero-shot generation produces geographically differentiated survey data. However, performance is strongly variable-dependent. Downstream effects in population synthesis are mixed, as IPF sometimes amplifies or reduces errors in the generated data. Spatial validation shows that LLM-based populations reproduce census tract-level patterns reasonably well, especially for variables that were more aligned with the ground truth data. Overall, the LLM-generated survey data shows promise as supplementary input, but not yet as a replacement for real survey data. |
| title | Using Zero-Shot LLM-Generated Survey Data for Geographically Explicit Population Synthesis |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2605.27401 |