# Schrodinger's Memory: Large Language Models

arXiv: https://arxiv.org/abs/2409.10482 · HTML: https://mlsanity.com/paper/2409.10482/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 40 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Builds on (most cited first, 21 of 21)

- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Sentiment Analysis in the Era of Large Language Models: A Reality Check](https://mlsanity.com/paper/2305.15005/) (2023)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models](https://mlsanity.com/paper/2309.12307/) (2023)
- [Memorizing Transformers](https://mlsanity.com/paper/2203.08913/) (2022)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [Measuring Forgetting of Memorized Training Examples](https://mlsanity.com/paper/2207.00099/) (2022)
- [A Critical Evaluation of Evaluations for Long-form Question Answering](https://mlsanity.com/paper/2305.18201/) (2023)
- [PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training](https://mlsanity.com/paper/2309.10400/) (2023)
- [Enhancing Financial Sentiment Analysis via Retrieval Augmented Large Language Models](https://mlsanity.com/paper/2310.04027/) (2023)
- [Adaptive Machine Translation with Large Language Models](https://mlsanity.com/paper/2301.13294/) (2023)
- [Extending Context Window of Large Language Models via Semantic Compression](https://mlsanity.com/paper/2312.09571/) (2023)
- [Pretraining-Based Natural Language Generation for Text Summarization](https://mlsanity.com/paper/1902.09243/) (2019)
- [Memory3: Language Modeling with Explicit Memory](https://mlsanity.com/paper/2407.01178/) (2024)
- [LongQLoRA: Efficient and Effective Method to Extend Context Length of Large Language Models](https://mlsanity.com/paper/2311.04879/) (2023)
- [Dynamic Universal Approximation Theory: Foundations for Parallelism in Neural Networks](https://mlsanity.com/paper/2407.21670/) (2024)

## Built on by (most cited first, 2 of 2)

- [Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures](https://mlsanity.com/paper/2508.10824/) (2025)
- [Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models](https://mlsanity.com/paper/2507.02870/) (2025)

## Abstract (arXiv)

Memory is the foundation of all human activities; without memory, it would be nearly impossible for people to perform any task in daily life. With the development of Large Language Models (LLMs), their language capabilities are becoming increasingly comparable to those of humans. But do LLMs have memory? Based on current performance, LLMs do appear to exhibit memory. So, what is the underlying mechanism of this memory? Previous research has lacked a deep exploration of LLMs' memory capabilities and the underlying theory. In this paper, we use Universal Approximation Theorem (UAT) to explain the memory mechanism in LLMs. We also conduct experiments to verify the memory capabilities of various LLMs, proposing a new method to assess their abilities based on these memory ability. We argue that LLM memory operates like Schr"odinger's memory, meaning that it only becomes observable when a specific memory is queried. We can only determine if the model retains a memory based on its output in response to the query; otherwise, it remains indeterminate. Finally, we expand on this concept by comparing the memory capabilities of the human brain and LLMs, highlighting the similarities and differences in their operational mechanisms.