Aspects of human memory and Large Language Models

Romuald A. Janik
11/7/2023
cs.CLcs.AIcs.LG

Official code: rmldj/memory-llm-paper (3 stars, MIT, last commit 2023-11-08).

Abstract

Large Language Models (LLMs) are huge artificial neural networks which primarily serve to generate text, but also provide a very sophisticated probabilistic model of language use. Since generating a semantically consistent text requires a form of effective memory, we investigate the memory properties of LLMs and find surprising similarities with key characteristics of human memory. We argue that the human-like memory properties of the Large Language Model do not follow automatically from the LLM architecture but are rather learned from the statistics of the training textual data. These results strongly suggest that the biological features of human memory leave an imprint on the way that we structure our textual narratives.

View on arXivView PDF

Code Implementations(1)

rmldj/memory-llm-paperOfficial100%
MIT

Code for the paper "Aspects of human memory and Large Language Models"

30PythonOct 16, 20232 years agoMIT

Similar Papers

To model human linguistic prediction, make LLMs less superhuman

88% match2025

Towards a Psychology of Machines: Large Language Models Predict Human Memory

88% match2024

A Multi-Perspective Analysis of Memorization in Large Language Models

88% match2024

Cognitive Memory in Large Language Models

87% match1 repo12025

Beyond Human-Like Processing: Large Language Models Perform Equivalently on Forward and Backward Scientific Text

87% match2024

The LLM Language Network: A Neuroscientific Approach for Identifying Causally Task-Relevant Units

87% match2 repos212024

Cite this paper

@article{janik2023aspects,
  title  = {Aspects of human memory and Large Language Models},
  author = {Romuald A. Janik},
  year   = {2023},
  eprint = {2311.03839},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.03839v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.03839.svg)](https://codeofpaper.com/paper/2311.03839)

Discussion