Unverified50% confidenceFactExact time
Traditionally, large model memory has mainly relied on three approaches: System Prompts, Retrieval-Augmented Generation (RAG), and Fine-tuning.
1
Sources
50%
Confidence
Long-term
Relevance
9/7/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe memory of LLMs depends on the context window, which is the maximum number of tokens the model can process in a single inference.74% similarUnverifiedFine-tuning is suitable for teaching a model a specific output style or domain tone, while RAG achieves immediate-update-ready results through an external knowledge base, and the two are often used in combination in engineering.72% similarVerifiedThe inference stage of large models is memory-bound (limited by memory bandwidth); generating each token requires reading the entire model weights from VRAM, resulting in extremely low computational intensity.72% similarUnverifiedMemory机制在大语言模型工程中对应系统提示词工程与外部记忆存储的结合，用于模拟无状态模型的持久化状态71% similarUnverified向量记忆可以随时增删实时更新，与大模型参数中硬编码的知识有本质区别，属于可持续扩展的外部记忆71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/871896API
curl https://kongchang.com/api/v1/knowledge/claims/871896MCP
get_claim(id=871896)