Article
Version 1
Preserved in Portico This version is not peer-reviewed
GPT-4 Can't Reason
Version 1
: Received: 27 July 2023 / Approved: 2 August 2023 / Online: 2 August 2023 (04:10:57 CEST)
Version 2 : Received: 3 August 2023 / Approved: 4 August 2023 / Online: 7 August 2023 (07:13:00 CEST)
Version 2 : Received: 3 August 2023 / Approved: 4 August 2023 / Online: 7 August 2023 (07:13:00 CEST)
How to cite: Arkoudas, K. GPT-4 Can't Reason. Preprints 2023, 2023080148. https://doi.org/10.20944/preprints202308.0148.v1 Arkoudas, K. GPT-4 Can't Reason. Preprints 2023, 2023080148. https://doi.org/10.20944/preprints202308.0148.v1
Abstract
GPT-4 was released in March 2023 to wide acclaim, marking a very substantial improvement across the board over GPT-3.5 (OpenAI's previously best model, which had powered the initial release of ChatGPT). Despite the genuinely impressive improvement, however, there are good reasons to be highly skeptical of GPT-4's ability to reason. This position paper discusses the nature of reasoning; criticizes the current formulation of reasoning problems in the NLP community and the way in which the reasoning performance of LLMs is currently evaluated; introduces a collection of 21 diverse reasoning problems; and performs a detailed qualitative analysis of GPT-4's performance on these problems. Based on the results of this analysis, the paper argues that, despite the occasional flashes of analytical brilliance, GPT-4 at present is utterly incapable of reasoning.
Keywords
GPT-4; LLM; AI; reasoning; inference
Subject
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright: This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Comments (0)
We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.
Leave a public commentSend a private comment to the author(s)
* All users must log in before leaving a comment