A Survey on the Real Power of ChatGPT

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Ming, Liu, Ran, Zhu, Ye, Wang, Hua, Qu, Youyang, Li, Rongsheng, Sheng, Yongpan, Buntine, Wray
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929338871447552
author Liu, Ming
Liu, Ran
Zhu, Ye
Wang, Hua
Qu, Youyang
Li, Rongsheng
Sheng, Yongpan
Buntine, Wray
author_facet Liu, Ming
Liu, Ran
Zhu, Ye
Wang, Hua
Qu, Youyang
Li, Rongsheng
Sheng, Yongpan
Buntine, Wray
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00704
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Survey on the Real Power of ChatGPT
Liu, Ming
Liu, Ran
Zhu, Ye
Wang, Hua
Qu, Youyang
Li, Rongsheng
Sheng, Yongpan
Buntine, Wray
Computation and Language
Artificial Intelligence
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.
title A Survey on the Real Power of ChatGPT
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2405.00704