Parametric knowledge
Parametric knowledge is information encoded in a model’s learned parameters through training, rather than supplied or retrieved from an external source at inference time.
Retrieval Augmented Generation, The Foundational Ideas
Parametric memory is knowledge encoded in the learned parameters of a trained model rather than retrieved from an external source.
- How it is used
- Frames when a language model can rely on learned weights versus requiring retrieval for current or externally verifiable information.
- How deep it goes
- Explains weight storage, frozen updates, hallucination, traceability, and tradeoffs with external retrieval, but not training mechanics.
- Examples
- Uses Paris’s capital, changing supply-chain conditions, recent legal rulings, clinical trials, and market developments as examples.
- What you can do after
- Evaluate when static model knowledge is insufficient and when retrieval can improve freshness, provenance, and domain specialization.
Read how Retrieval Augmented Generation, The Foundational Ideas explains parametric knowledge →
LLM Evaluation and Alignment, The Foundational Ideas
Parametric knowledge is information encoded in a model’s learned parameters rather than retrieved from an external source at inference time.
- How it is used
- Supports hallucination detection by distinguishing claims grounded in retrieved context from claims generated from learned parameters.
- How deep it goes
- Defines storage in model parameters and explains consistency-based detection, but does not descend into parameter-level retrieval internals.
- Examples
- Uses repeated paper-authorship questions to contrast stable factual recall with variable hallucinated details.
- What you can do after
- Evaluate generated claims by routing grounded content to reference checks and ungrounded content to consistency-based checks.
Read how LLM Evaluation and Alignment, The Foundational Ideas explains parametric knowledge →
Context Engineering
Parametric memory is knowledge embedded in a model’s parameters through training.
- How it is used
- Supplies general facts, language patterns, and reasoning heuristics implicitly during inference.
- How deep it goes
- Defines where it resides and what it contains, but does not explain how training encodes it.
- Examples
- Illustrates its contents through general facts, language patterns, and reasoning heuristics.
- What you can do after
- Understand how model-internal knowledge differs from externally managed memory in agent systems.
Read how Context Engineering explains parametric knowledge →
What to know first
- hallucinationA hallucination is model-generated content that is false, fabricated, or unsupported by relevant evidence but presented as plausible or factual.
- knowledge baseA knowledge base is an organized body or representation of information that people or computational systems can consult to support retrieval, reference, reasoning, or tasks.
- language modelA language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- parameterA parameter is a value or named input that specifies or influences the behavior, computation, or output of a function, model, or system.
Related concepts
- retrieval-augmented generationused by · Retrieval-augmented generation is a technique that retrieves relevant information from external sources and supplies it as context to a generative model when producing an output.
- external memorycontrasts with · External memory is an addressable store of information maintained outside a model’s learned parameters or immediate context and made available for later retrieval.
- language modelpart of · A language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
- memorykind of · Memory is a storage capability or mechanism for retaining information or computational state for later access or use.
- fine-tuningconfigured by · Fine-tuning is the continued training of a pretrained model on targeted data or objectives to adapt its parameters or behavior to a task, domain, or use.
Questions about parametric knowledge
What is parametric knowledge?
Parametric knowledge is information encoded in a model’s learned parameters through training, rather than supplied or retrieved from an external source at inference time.
Which Manning books explain parametric knowledge?
Retrieval Augmented Generation, The Foundational Ideas, LLM Evaluation and Alignment, The Foundational Ideas and Context Engineering.
What should I know before learning parametric knowledge?
Manning books that teach parametric knowledge usually introduce hallucination, knowledge base, language model and parameter first.
What is the difference between parametric knowledge and external memory?
Parametric knowledge is information encoded in a model’s learned parameters through training, rather than supplied or retrieved from an external source at inference time. External memory is an addressable store of information maintained outside a model’s learned parameters or immediate context and made available for later retrieval.
What is parametric knowledge a kind of?
Parametric knowledge is a kind of memory. Memory is a storage capability or mechanism for retaining information or computational state for later access or use.
What is parametric knowledge part of?
Parametric knowledge is part of language model. A language model is a computational model that represents patterns in linguistic sequences to assign probabilities, predict, generate, or evaluate language.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.


