English

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.

Keywords

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