principles.fyi · the brain · concept

conditional generation

Generating output that is steered by a given input — write Y, but conditioned on X.

P(output | input) — next tokens depend on the given input

Conditional generation means the text a model writes is shaped by something you give it: a prompt, a source sentence to translate, a document to summarize. Formally the model produces P(output | input) — the probability of each next token given everything provided so far. Encoder-decoders make the conditioning structural (the decoder cross-attends to the encoded input), while decoder-only models do it by simply placing the input in the context window and continuing from it. Every time you prompt a chat model, you are doing conditional generation.