Simulating Human Memory with Language Models

• URL: http://arxiv.org/abs/2605.25680v1
• Date: Mon, 25 May 2026 10:39:08 GMT
• Title: Simulating Human Memory with Language Models
• Abstract summary: We show that out-of-the-box language models exhibit better memory than humans, even when prompted to imitate human behavior.<n>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.
• Score: 15.781024764769024
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Unlocking the Working Memory of Large Language Models for Latent Reasoning [21.924207996049407]
  Reasoning in Memory (RiM) is a latent reasoning method that replaces the autoregressive generation of reasoning steps with memory blocks.<n>RiM matches or exceeds existing latent reasoning methods while avoiding the autoregressive generation of thoughts.
  arXiv  Detail & Related papers  (2026-05-28T17:59:49Z)
• Human-like fleeting memory improves language learning but impairs reading time prediction in transformer language models [0.0]
  We investigate the hypothesized benefit of fleeting memory for language learning in experiments on transformer language models.<n>We find that fleeting memory consistently improves language learning but, unexpectedly, impairs surprisal-based prediction of human reading times.
  arXiv  Detail & Related papers  (2025-08-07T19:17:53Z)
• DevBench: A multimodal developmental benchmark for language learning [0.34129029452670606]
  We introduce DevBench, a benchmark for evaluating vision-language models on tasks and behavioral data.<n>We show that DevBench provides a benchmark for comparing models to human language development.<n>These comparisons highlight ways in which model and human language learning processes diverge.
  arXiv  Detail & Related papers  (2024-06-14T17:49:41Z)
• Aspects of human memory and Large Language Models [0.0]
  Large Language Models (LLMs) are huge artificial neural networks which primarily serve to generate text. We find surprising similarities with key characteristics of human memory.
  arXiv  Detail & Related papers  (2023-11-07T09:39:12Z)
• Retentive or Forgetful? Diving into the Knowledge Memorizing Mechanism of Language Models [49.39276272693035]
  Large-scale pre-trained language models have shown remarkable memorizing ability. Vanilla neural networks without pre-training have been long observed suffering from the catastrophic forgetting problem. We find that 1) Vanilla language models are forgetful; 2) Pre-training leads to retentive language models; 3) Knowledge relevance and diversification significantly influence the memory formation.
  arXiv  Detail & Related papers  (2023-05-16T03:50:38Z)
• Chain of Hindsight Aligns Language Models with Feedback [62.68665658130472]
  We propose a novel technique, Chain of Hindsight, that is easy to optimize and can learn from any form of feedback, regardless of its polarity. We convert all types of feedback into sequences of sentences, which are then used to fine-tune the model. By doing so, the model is trained to generate outputs based on feedback, while learning to identify and correct negative attributes or errors.
  arXiv  Detail & Related papers  (2023-02-06T10:28:16Z)
• Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies [7.696359453385686]
  We introduce a new type of test, called a Turing Experiment (TE) A TE can reveal consistent distortions in a language model's simulation of a specific human behavior. We compare how well different language models are able to reproduce classic economic, psycholinguistic, and social psychology experiments.
  arXiv  Detail & Related papers  (2022-08-18T17:54:49Z)
• Training Language Models with Memory Augmentation [28.4608705738799]
  We present a novel training approach designed for training language models with memory augmentation. Our approach uses a training objective that directly takes in-batch examples as accessible memory. We demonstrate significant gains over previous memory-augmented approaches.
  arXiv  Detail & Related papers  (2022-05-25T11:37:29Z)
• Training Language Models with Natural Language Feedback [51.36137482891037]
  We learn from language feedback on model outputs using a three-step learning algorithm. In synthetic experiments, we first evaluate whether language models accurately incorporate feedback to produce refinements. Using only 100 samples of human-written feedback, our learning algorithm finetunes a GPT-3 model to roughly human-level summarization.
  arXiv  Detail & Related papers  (2022-04-29T15:06:58Z)
• LaMemo: Language Modeling with Look-Ahead Memory [50.6248714811912]
  We propose Look-Ahead Memory (LaMemo) that enhances the recurrence memory by incrementally attending to the right-side tokens. LaMemo embraces bi-directional attention and segment recurrence with an additional overhead only linearly proportional to the memory length. Experiments on widely used language modeling benchmarks demonstrate its superiority over the baselines equipped with different types of memory.
  arXiv  Detail & Related papers  (2022-04-15T06:11:25Z)
• Paraphrastic Representations at Scale [134.41025103489224]
  We release trained models for English, Arabic, German, French, Spanish, Russian, Turkish, and Chinese languages. We train these models on large amounts of data, achieving significantly improved performance from the original papers.
  arXiv  Detail & Related papers  (2021-04-30T16:55:28Z)
• Comparison of Interactive Knowledge Base Spelling Correction Models for Low-Resource Languages [81.90356787324481]
  Spelling normalization for low resource languages is a challenging task because the patterns are hard to predict. This work shows a comparison of a neural model and character language models with varying amounts on target language data. Our usage scenario is interactive correction with nearly zero amounts of training examples, improving models as more data is collected.
  arXiv  Detail & Related papers  (2020-10-20T17:31:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.