Equation 11 · Part 1 · How Constitutional AI Actually Constrains a Model's Behavior
Symbol L^AI_PM
What this part means
M is computed from the expected values combined on the right.
Its job in the formula
M is computed from the expected values combined on the right.
Full expression→Symbol L^AI_PM→Article meaning
The passage around this formula
Nothing in that loss distinguishes where a pair came from; a human-labeled winner and an AI-labeled winner are interchangeable once written down as (x, , ) . That is the precise, narrow sense in which Constitutional AI “differs mechanically from plain RLHF”: it changes the labeling function for one half of one dataset, not the loss, not the optimizer, not the use of a KL penalty against the supervised policy. For the soft-labeled AI comparisons specifically, where the feedback model outputs a probability p of preferring response over rather than a hard choice, the corresponding cross-entropy term is . which exposes the other genuine mechanical difference:…
Learn the underlying idea
A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.
Open the illustrated subscripts: which member of a family? guide →
See this notation across published equations →
Sources cited in the article section
These citations provide research context; check each source for the exact claim it supports.