Papers
arxiv:2605.25680

Simulating Human Memory with Language Models

Published on May 25
Authors:
,
,
,
,

Abstract

Language models demonstrate superior memory performance compared to humans in psychological experiments, but with improved prompting and compactor techniques, they can simulate more human-like forgetting patterns for better user simulation in educational applications.

AI-generated summary

Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap, we run a series of classic memory experiments from psychology on both humans and language models. Across tasks, we find that out-of-the-box language models exhibit better memory than humans, even when prompted to imitate human behavior. We then show that better prompting strategies and the use of a compactor can cause language models to forget content in a more human-like way. Using these methods, we show preliminary evidence that language models with human-like memory constraints can function as more effective user simulators in a downstream education task. Finally, we release human reference data and benchmarks to support future work on simulating human memory with language models.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.25680
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.25680 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.25680 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.25680 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.