GPT-4 Shows Comparable Performance to Human Examiners in Ranking Open-Text Answers

This repository contains all datasets used in the research paper:
"GPT-4 Shows Comparable Performance to Human Examiners in Ranking Open-Text Answers"

Files and Descriptions

1. Data_complete_Can_GPT_Replace_Human_Examiners.xlsx
   Contains two sheets:

• Data – Main analysis dataset for Ranking and Point Assessment of Five Answers.

• Robustness & Extensions – Data for Robustness & Extensions, covering Ranking and Point Assessment of Five Answers.

1. point_assessment_single_answer_all_robustness_score.xlsx
   Contains all data related to robustness checks for Point Assessment of Single Answers.

2. point_assessment_single_answer.xlsx
   Contains the main dataset for Point Assessment of Single Answers (excluding robustness checks).

Note: Any variable termed GPT is output of the model as under OpenAI Terms & policies.