Working Memory Capacity of ChatGPT: An Empirical Study

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gong, Dongyu, Wan, Xingchen, Wang, Dingmin
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911769343033344
author Gong, Dongyu
Wan, Xingchen
Wang, Dingmin
author_facet Gong, Dongyu
Wan, Xingchen
Wang, Dingmin
contents Working memory is a critical aspect of both human intelligence and artificial intelligence, serving as a workspace for the temporary storage and manipulation of information. In this paper, we systematically assess the working memory capacity of ChatGPT, a large language model developed by OpenAI, by examining its performance in verbal and spatial n-back tasks under various conditions. Our experiments reveal that ChatGPT has a working memory capacity limit strikingly similar to that of humans. Furthermore, we investigate the impact of different instruction strategies on ChatGPT's performance and observe that the fundamental patterns of a capacity limit persist. From our empirical findings, we propose that n-back tasks may serve as tools for benchmarking the working memory capacity of large language models and hold potential for informing future efforts aimed at enhancing AI working memory.
format Preprint
id arxiv_https___arxiv_org_abs_2305_03731
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Working Memory Capacity of ChatGPT: An Empirical Study
Gong, Dongyu
Wan, Xingchen
Wang, Dingmin
Artificial Intelligence
Computation and Language
Neurons and Cognition
Working memory is a critical aspect of both human intelligence and artificial intelligence, serving as a workspace for the temporary storage and manipulation of information. In this paper, we systematically assess the working memory capacity of ChatGPT, a large language model developed by OpenAI, by examining its performance in verbal and spatial n-back tasks under various conditions. Our experiments reveal that ChatGPT has a working memory capacity limit strikingly similar to that of humans. Furthermore, we investigate the impact of different instruction strategies on ChatGPT's performance and observe that the fundamental patterns of a capacity limit persist. From our empirical findings, we propose that n-back tasks may serve as tools for benchmarking the working memory capacity of large language models and hold potential for informing future efforts aimed at enhancing AI working memory.
title Working Memory Capacity of ChatGPT: An Empirical Study
topic Artificial Intelligence
Computation and Language
Neurons and Cognition
url https://arxiv.org/abs/2305.03731