Latent Space
Definition of latent space in machine learning, LLMs, and embeddings.
Latent Space #
A latent space, also called an embedding space, is an abstract high-dimensional representation where a model maps similar items to nearby vectors. It is usually learned automatically from data: latent variables capture hidden features and arrange items across a manifold that is often smaller and easier to compute over than the raw feature space.
In large language models, tokens and hidden states live in latent space, where semantic relationships between words, phrases, prompts, and responses are encoded before being decoded back into language.
Example: A model can place "cat" and "dog" near each other in latent space because both share semantic features, while placing "invoice" farther away.
Dictionary: https://dictionary.platphormnews.com/en/define/latent-space
Related Documentation
Latent-Space Fine-Tuning
Definition of LoRA, adapters, AWS SageMaker, and Bedrock as latent-space adaptation workflows.
Latent Space Surgery
Definition of targeted model editing through concept directions in latent space.
Latent Operations
Definition of vector shifts, interpolation, slicing, masking, and sampling in latent space.
Latent Reasoning
Definition of latent reasoning in LLM hidden states and continuous representations.
Embedding Space
Definition of embedding space as a vector representation for semantic similarity and retrieval.