This is the repo for the AAAI submission called "Do Large Language Models Learn Human-Like Preference?"

The code, data, and figures associated with each of the experiments is stored in the associated top level folder. Each of the folders contains the code used to conduct the experimental analysis while the code used to conduct the experiments is housed in the ipynb file in the top level.

The data file target must be set in the experiment notebook with the desired location to store the results. The output from the experiments is stored in the data folders in each experiment folder while the input data is stored in the top level of each of the experiment folders.