Representation Bias in Political Sample Simulations with Large Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910529063223296 |
|---|---|
| author | Qi, Weihong Lyu, Hanjia Luo, Jiebo |
| author_facet | Qi, Weihong Lyu, Hanjia Luo, Jiebo |
| contents | This study seeks to identify and quantify biases in simulating political samples with Large Language Models, specifically focusing on vote choice and public opinion. Using the GPT-3.5-Turbo model, we leverage data from the American National Election Studies, German Longitudinal Election Study, Zuobiao Dataset, and China Family Panel Studies to simulate voting behaviors and public opinions. This methodology enables us to examine three types of representation bias: disparities based on the the country's language, demographic groups, and political regime types. The findings reveal that simulation performance is generally better for vote choice than for public opinions, more accurate in English-speaking countries, more effective in bipartisan systems than in multi-partisan systems, and stronger in democratic settings than in authoritarian regimes. These results contribute to enhancing our understanding and developing strategies to mitigate biases in AI applications within the field of computational social science. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_11409 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Representation Bias in Political Sample Simulations with Large Language Models Qi, Weihong Lyu, Hanjia Luo, Jiebo Computation and Language This study seeks to identify and quantify biases in simulating political samples with Large Language Models, specifically focusing on vote choice and public opinion. Using the GPT-3.5-Turbo model, we leverage data from the American National Election Studies, German Longitudinal Election Study, Zuobiao Dataset, and China Family Panel Studies to simulate voting behaviors and public opinions. This methodology enables us to examine three types of representation bias: disparities based on the the country's language, demographic groups, and political regime types. The findings reveal that simulation performance is generally better for vote choice than for public opinions, more accurate in English-speaking countries, more effective in bipartisan systems than in multi-partisan systems, and stronger in democratic settings than in authoritarian regimes. These results contribute to enhancing our understanding and developing strategies to mitigate biases in AI applications within the field of computational social science. |
| title | Representation Bias in Political Sample Simulations with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2407.11409 |