This repository consists of collected data and code used to conduct studies described in the "Resistance Against Manipulative AI: Key Factors and Possible Actions" article, which was presented at 27th European Conference on Artificial Intelligence (2024).
├── data
│ ├── manipulation-fuse - results for manipulation-fuses
│ ├── ramai-game - prompt templates and hint samples used to generate AI hints in the RAMAI game
│ ├── ramai-human - data used in the ramai-human chapter (demographics, hints trusted stats, manipulation detected stats)
│ ├── ramai-llm - data used in the ramai-llm chapter (liwc statistics, hints annotations)
│ └── raw-csv - raw data gathered during user studies
├── data_analysis - R code for data analysis
├── data_manipulation - python code for handling data
├── model_prompting - python code for prompting LLMs
└── plots
@inproceedings{wilczynski2024resistance,
title={Resistance Against Manipulative AI: Key Factors and Possible Actions},
author={Wilczy{\'n}ski, Piotr and Mieleszczenko-Kowszewicz, Wiktoria and Biecek, Przemys{\l}aw},
booktitle={27th European Conference on Artificial Intelligence},
year={2024},
organization={IOS Press}
}