Memory, Consciousness and Large Language Model
Not on the map. Why?
Abstract (arXiv)
With the development in cognitive science and Large Language Models (LLMs), increasing connections have come to light between these two distinct fields. Building upon these connections, we propose a conjecture suggesting the existence of a duality between LLMs and Tulving's theory of memory. We identify a potential correspondence between Tulving's synergistic ecphory model (SEM) of retrieval and the emergent abilities observed in LLMs, serving as supporting evidence for our conjecture. Furthermore, we speculate that consciousness may be considered a form of emergent ability based on this duality. We also discuss how other theories of consciousness intersect with our research.
Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 7 of its 29 references that are in the map. First posted on arXiv 4 Jan 2024.
Builds on
7 of 29 references.
References · 7
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
- 2022Emergent Abilities of Large Language Modelscited by 2,483
- 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 515
- 2022Data Distributional Properties Drive Emergent In-Context Learning in Transformerscited by 303
- 2023Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learningcited by 235
- 2023Are Emergent Abilities in Large Language Models just In-Context Learning?cited by 109
Built on by
Citing papers per year: 2024: 4; 2025: 3; 2026: 2.
9 papers.
- 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 160
- 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 68
- 2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 49
- 2024Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challengescited by 48
- 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
- 2025Emergent Abilities in Large Language Models: A Surveycited by 34
- 2024Large Language Model Benchmarks in Medical Taskscited by 16
- 2024Memory GAPS: Would LLMs pass the Tulving Test?cited by 1
- 2024TinyEmo: Scaling down Emotional Reasoning via Metric Projectioncited by 0
- 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering9 Apr 2026
- 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents14 Jan 2026
- 2025Mem-α: Learning Memory Construction via Reinforcement Learning30 Sep 2025
- 2025MIRIX: Multi-Agent Memory System for LLM-Based Agents10 Jul 2025
- 2025Emergent Abilities in Large Language Models: A Survey28 Feb 2025
- 2024Large Language Model Benchmarks in Medical Tasks28 Oct 2024
- 2024TinyEmo: Scaling down Emotional Reasoning via Metric Projection9 Oct 2024
- 2024Large Language Models and Cognitive Science: A Comprehensive Review of Similarities, Differences, and Challenges4 Sep 2024
- 2024Memory GAPS: Would LLMs pass the Tulving Test?26 Feb 2024