A Categorical Archive of ChatGPT Failures
This work addresses the problem of understanding and mitigating failures in large language models for researchers and developers, though it is incremental as it categorizes known issues rather than proposing new solutions.
The study tackled the lack of comprehensive analysis of ChatGPT's failures by identifying and discussing eleven categories of failures, such as reasoning, factual errors, math, coding, and bias, to highlight risks and societal implications.
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, limitations, and societal implications of ChatGPT are also highlighted. The goal of this study is to assist researchers and developers in enhancing future language models and chatbots.