Equation 4 · 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 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 β
β is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.
How to interpret it
Read this expression with the definitions, units, and assumptions supplied by the article.
What the article says around this equation
where sets the strength of the KL penalty and the pretraining mixture, with set to zero for the plain PPO models [ 4 ] . Direct preference optimisation later showed that the explicit reward model can be dispensed with entirely — the optimal policy under this objective has a closed form, so the same problem can be solved with a classification loss on the preference pairs [ 15 ] . That is an important simplification, and it changes nothing about the present argument. DPO removes the reward network; it does not remove the reward. The objective is still rater approval, and the KL term is still there, folded into the loss.
Sources cited in the surrounding passage
- [4] Training Language Models to Follow Instructions with Human Feedback ↗
- [15] Direct Preference Optimization: Your Language Model is Secretly a Reward Model ↗
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