parametric memory

Parametric memory is the knowledge a language model stores in its weights during training and recalls without external retrieval.

1 articleLast mentioned

Parametric memory refers to knowledge that a neural network has learned from its training data and stored implicitly in its weights, or parameters. It is the knowledge a large language model draws on when answering without any external documents or tools, and is also called parametric knowledge.

The contrasting concept is non-parametric memory, in which material outside the model, such as a search engine or document store, is retrieved at inference time. Retrieval-augmented generation (RAG) is a representative method that combines the two. Because parametric memory cannot contain information after the training data cutoff and updating it requires retraining or fine-tuning, tasks that depend on current information typically pair it with external data sources.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • Samaya AI Earnings Benchmark: Frontier Models Edge Out Analyst ConsensusAI Performance ·

    With parametric knowledge alone, meaning no retrieval and only what the model memorized in training, surprise correlation collapsed to 0.11 for GPT-6 Astra and…

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.