Cognitive Memory in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shan, Lianlei, Luo, Shixian, Zhu, Zezhou, Yuan, Yu, Wu, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913806388559872
author Shan, Lianlei
Luo, Shixian
Zhu, Zezhou
Yuan, Yu
Wu, Yong
author_facet Shan, Lianlei
Luo, Shixian
Zhu, Zezhou
Yuan, Yu
Wu, Yong
contents This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures. The text-based memory section covers acquisition (selection and summarization), management (updating, accessing, storing, and resolving conflicts), and utilization (full-text search, SQL queries, semantic search). The KV cache-based memory section discusses selection methods (regularity-based summarization, score-based approaches, special token embeddings) and compression techniques (low-rank compression, KV merging, multimodal compression), along with management strategies like offloading and shared attention mechanisms. Parameter-based memory methods (LoRA, TTT, MoE) transform memories into model parameters to enhance efficiency, while hidden-state-based memory approaches (chunk mechanisms, recurrent transformers, Mamba model) improve long-text processing by combining RNN hidden states with current methods. Overall, the paper offers a comprehensive analysis of LLM memory mechanisms, highlighting their significance and future research directions.
format Preprint
id arxiv_https___arxiv_org_abs_2504_02441
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Cognitive Memory in Large Language Models
Shan, Lianlei
Luo, Shixian
Zhu, Zezhou
Yuan, Yu
Wu, Yong
Computation and Language
Artificial Intelligence
This paper examines memory mechanisms in Large Language Models (LLMs), emphasizing their importance for context-rich responses, reduced hallucinations, and improved efficiency. It categorizes memory into sensory, short-term, and long-term, with sensory memory corresponding to input prompts, short-term memory processing immediate context, and long-term memory implemented via external databases or structures. The text-based memory section covers acquisition (selection and summarization), management (updating, accessing, storing, and resolving conflicts), and utilization (full-text search, SQL queries, semantic search). The KV cache-based memory section discusses selection methods (regularity-based summarization, score-based approaches, special token embeddings) and compression techniques (low-rank compression, KV merging, multimodal compression), along with management strategies like offloading and shared attention mechanisms. Parameter-based memory methods (LoRA, TTT, MoE) transform memories into model parameters to enhance efficiency, while hidden-state-based memory approaches (chunk mechanisms, recurrent transformers, Mamba model) improve long-text processing by combining RNN hidden states with current methods. Overall, the paper offers a comprehensive analysis of LLM memory mechanisms, highlighting their significance and future research directions.
title Cognitive Memory in Large Language Models
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2504.02441