A common PPO-based pipeline trains a reward model and samples policy responses during updates. DPO instead trains on preference pairs using the policy and a frozen reference.
panel 1 · training components
DPO avoids a separate reward-model fit and online response sampling during its updates.
preference data → reward model → sampler → policy
Components in one common setup: policy · reference · reward · value
panel 2 · the mechanism
One illustrative preference pair. Scripted log-ratio changes show how the margin affects loss; β = 0.1.
← below reference (gray)above reference (amber) →
DPO loss0.69
DPO favors a larger chosen-minus-rejected log-ratio margin. That does not guarantee that the chosen response’s absolute probability rises on every update. The reference defines the comparison; it does not impose a hard maximum KL distance. These bars are scripted examples, not learned policy updates.