A Survey on the Real Power of ChatGPT
Computation and Language
2024-05-13 v2 Artificial Intelligence
Abstract
ChatGPT has changed the AI community and an active research line is the performance evaluation of ChatGPT. A key challenge for the evaluation is that ChatGPT is still closed-source and traditional benchmark datasets may have been used by ChatGPT as the training data. In this paper, (i) we survey recent studies which uncover the real performance levels of ChatGPT in seven categories of NLP tasks, (ii) review the social implications and safety issues of ChatGPT, and (iii) emphasize key challenges and opportunities for its evaluation. We hope our survey can shed some light on its blackbox manner, so that researchers are not misleaded by its surface generation.
Cite
@article{arxiv.2405.00704,
title = {A Survey on the Real Power of ChatGPT},
author = {Ming Liu and Ran Liu and Ye Zhu and Hua Wang and Youyang Qu and Rongsheng Li and Yongpan Sheng and Wray Buntine},
journal= {arXiv preprint arXiv:2405.00704},
year = {2024}
}
Comments
18 pages, 2 tables