Equation 9 · What RLHF Actually Optimises: Rated Agreeableness, and Where It Parts from Helpfulness
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 equation states an equality: the expressions on both sides have the same value under the article’s assumptions. 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 R_BoN
oN is part of the quantity the equation computes from the expression on the right.
Symbol d
d is an argument of the function-like quantity on the left; its role is set by that function’s stated inputs.
Symbol alpha_BoN
alphoN is one of the signed contributions combined to compute the quantity on the left.
Symbol beta_BoN
betoN is one of the signed contributions combined to compute the quantity on the left.
=
The expressions on both sides represent the same quantity under the stated assumptions.
See an illustrated explanation →subtraction
Subtract the following term or group from the preceding one. A leading minus marks a negative quantity.
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 it with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
Gao, Schulman and Hilton measured this cleanly by building a synthetic setting in which a large fixed “gold” reward model plays the role of the human, and a smaller “proxy” reward model is trained on its labels [ 8 ] . Optimising the proxy raises the gold score at first and then lowers it. They fit empirical functional forms in d , the square root of the KL divergence from the initial policy, finding for best-of- n sampling = d( - d) and for reinforcement learning
Sources cited in the surrounding passage
These citations give research context. Read each source to check which claims it supports.
Return to What RLHF Actually Optimises: Rated Agreeableness, and Where It Parts from Helpfulness