preprintResearch SquareMay 9, 2023GREEN OA

A Categorical Archive of ChatGPT Failures

Indexed incrossref

Abstract

Abstract Large language models have been demonstrated to be valuable in different fields. ChatGPT, developed by OpenAI, has been trained using massive amounts of data and simulates human conversation by comprehending context and generating appropriate responses. It has garnered significant attention due to its ability to effectively answer a broad range of human inquiries, with fluent and comprehensive answers surpassing prior public chatbots in both security and usefulness. However, a comprehensive analysis of ChatGPT’s failures is lacking, which is the focus of this study. Eleven categories of failures, including reasoning, factual errors, math, coding, and bias, are presented and discussed. The risks,…

Citation impact

419
total citations
FWCI
Percentile
References
71
Citations per year

Authors

1

Topics & keywords

Keywords
  • Conversation
  • Computer science
  • Data science
  • Categorical variable
  • Context (archaeology)
  • Coding (social sciences)
  • Focus (optics)
  • Artificial intelligence
UN Sustainable Development Goals
  • Quality Education
No related works found for this paper.