mlsanityData to 14 Oct 2026

Working Memory Capacity of ChatGPT: An Empirical Study

arXiv 2305.03731 ↗First posted 30 Apr 2023cs.AI cs.CL q-bio.NCcited by 23

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 18 of its 50 references that are in the map. First posted on arXiv 30 Apr 2023.

Builds on

18 of 50 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  5. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2022Emergent Abilities of Large Language Modelscited by 2,512
  8. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,195
  9. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,135
  10. 2021Cross-Task Generalization via Natural Language Crowdsourcing Instructionscited by 699
  11. 2021Learning To Retrieve Prompts for In-Context Learningcited by 648
  12. 2021MetaICL: Learning to Learn In Contextcited by 454
6 more
  1. 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 384
  2. 2022Fine-tuning language models to find agreement among humans with diverse preferencescited by 189
  3. 2021Reframing Instructional Prompts to GPTk's Languagecited by 176
  4. 2022Large Language Models with Controllable Working Memorycited by 169
  5. 2021Meta-learning via Language Model In-context Tuningcited by 164
  6. 2020The Turking Test: Can Language Models Understand Instructions?cited by 82

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 9; 2026: 7.

23 papers.

Sort:

By area:

  1. 2024A Survey on Large Language Model-Based Game Agentscited by 112
  2. 2024Understanding the Dark Side of LLMs' Intrinsic Self-Correctioncited by 42
  3. 2025Consistently Simulating Human Personas with Multi-Turn Reinforcement Learningcited by 39
  4. 2023An In-depth Survey of Large Language Model-based Artificial Intelligence Agentscited by 31
  5. 2025Temporal Working Memory: Query-Guided Segment Refinement for Enhanced Multimodal Understandingcited by 28
  6. 2025Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Lengthcited by 20
  7. 2025Triangulating LLM Progress through Benchmarks, Games, and Cognitive Testscited by 12
  8. 2025United Minds or Isolated Agents? Exploring Coordination of LLMs under Cognitive Load Theorycited by 10
  9. 2025On the Failure of Latent State Persistence in Large Language Modelscited by 9
  10. 2025GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understandingcited by 9
  11. 2024Towards Building Specialized Generalist AI with System 1 and System 2 Fusioncited by 8
  12. 2025Whither symbols in the era of advanced neural networks?cited by 7
11 more
  1. 2025Strong Memory, Weak Control: An Empirical Study of Executive Functioning in LLMscited by 6
  2. 2024Self-Attention Limits Working Memory Capacity of Transformer-Based Modelscited by 5
  3. 2024CURATe: Benchmarking Personalised Alignment of Conversational AI Assistantscited by 5
  4. 2026A Neuropsychologically Grounded Evaluation of LLM Cognitive Abilitiescited by 5
  5. 2026Evaluating Cognitive Age Alignment in Interactive AI Agentscited by 2
  6. 2026M3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Taskscited by 2
  7. 2024Do Language Models Understand the Cognitive Tasks Given to Them? Investigations with the N-Back Paradigmcited by 1
  8. 2026In-context superposition: human-like working memory interference in large language modelscited by 1
  9. 2026Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgetscited by 1
  10. 2026A Dual-Task Paradigm to Investigate Sentence Comprehension Strategies in Language Modelscited by 0
  11. 2026In-Context Binding Capacity in Language Modelscited by 0