the.ai

Structure / Decoding

verified

Schema Conformance

The output has to be JSON matching a declared schema — the right keys, the right types, the enum values you listed. It is what makes a model callable from a program rather than readable by a person, and it is the boundary where a language model becomes a component instead of a conversation.

Viz primitive · budget-splitconformant-but-wrong = 6

conformant-but-wrong holds 17% of the budget; rest holds the remaining 83%.

Outputs that match the schema perfectly and say the wrong thing, against the ones that are also right, in outputs. Drag the schema's tightness up to watch conformity rise without correctness following — the gap is invisible to every check the schema runs.

6

Reviewed by opendroid · 2026-08-18

  • arXiv:2201.11227 — Synchromesh: Reliable code generation from pre-trained language models
  • arXiv:2403.06988 — Guiding LLMs The Right Way: Fast, Non-Invasive Constrained Generation