Techniques & Methods
Knowledge Representation
Knowledge representation (KR) concerns how AI systems encode information so it can be reasoned over. Approaches include semantic networks, ontologies, knowledge graphs, logical formalisms (first-order logic), and frame-based systems. Each balances expressivity against computational tractability.
In modern AI, knowledge representation is both explicit (knowledge graphs like Wikidata or domain ontologies) and implicit (distributed representations in LLM weights). RAG systems combine both: explicit retrieval from knowledge bases with implicit reasoning from LLMs.
Authority Links
Related Terms
Miscellaneous
Knowledge Base
Centralized repository of structured and unstructured information used to provide AI systems with domain knowledge.
Techniques & Methods
Semantic Annotation
Adding semantic metadata to content to improve AI understanding and processing.
Core Concepts
Entities
Specific, identifiable elements like names, places, and dates extracted from text.
Techniques & Methods
Retrieval Augmented Generation (RAG)
An inference-time architecture that retrieves relevant documents from a knowledge base or web index and injects them into a language model's context before generation, grounding answers in real source material.