Equation 5 · How Constitutional AI Actually Constrains a Model's Behavior
What does this equation mean?
Read the formula alongside the article passage below. Each part has a deeper page with its role in the equation, the supporting passage and nearby citations.
This mathematical expression combines the displayed quantities; its precise role follows from the surrounding article text. Read the equation part by part below; each part has a contextual explanation and a link to its mathematical background.
Read it piece by piece
Symbol y_w
is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
Symbol y_l
is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
subscript
The lower label selects a particular version, component, or indexed member of the quantity. For example, x₀ and xₜ can be values at different positions.
How to interpret it
Read this expression with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
Crucially, this AI-generated harmlessness comparison data did not replace human comparison data outright; it was combined with it. The paper reports 135,296 human helpfulness comparisons and 182,831 constitutionally generated harmlessness comparisons feeding one preference model, trained on the union of both, in the authors’ words: “we use human labels for helpfulness, but only AI labels for harmlessness.” A single Bradley-Terry-style preference loss is fit across both sources at once. Writing for the human comparison set, for the AI-generated set, for the reward model, x for a prompt, and , for the winning and losing response in a pair, the objective is
Sources cited in the article section
These citations give research context. Read each source to check which claims it supports.
Return to How Constitutional AI Actually Constrains a Model's Behavior