Authors: Liwei Jiang, Taylor Sorensen, Sydney Levine Yejin Choi,
This is the codebase for the paper.
We transformed the World Values Survey into natural languagestatements that describes people's values and preferences.
For downloading the raw World Values Survey data (Wave 7), please visit the official WVS website and follow their downloading instructions.
data/WVS_conversion.pycontains the code for data conversion.
-
data/demographics_meta_data.csvcontains the meta data of the demographics questions. -
data/refined_statements_meta_data.csvcontains the meta data of the refined statements. -
data/statements_meta_data.csvcontains the meta data of the polarity-grouped statements.
Please find the converted human label data here.
-
demographics_in_nl_refined_statements_combined_full_set.csvcontains converted human label data with refined statements. -
demographics_in_nl_statements_combined_full_set.csvcontains converted human label data with polarity-grouped statements.
src/prepare_data/compile_wvs_statements.pycontains the code for data conversion.
If you find our work helpful, please feel free to cite our work!
@misc{jiang2024indievalue,
title={Can Language Models Reason about Individualistic Human Values and Preferences?},
author={Liwei Jiang and Taylor Sorensen and Sydney Levine and Yejin Choi},
year={2024},
eprint={2410.0386
4E61
8},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2410.03868},
}