passdrill
AI & LLM Engineering · Fine-tuning & Model Customisation · Card 003/010 medium

A team wants to align a supervised-fine-tuned language model to human preference data (pairs of a preferred and a dispreferred response to the same prompt) without the engineering overhead of training a separate reward model and then running an online reinforcement-learning loop like PPO against it. They adopt Direct Preference Optimization (DPO). What does DPO actually do differently from that standard RLHF pipeline?

  1. It uses the closed-form relationship between an optimal KL-regularized policy and its implied reward under the Bradley-Terry preference model to rewrite the reward directly in terms of the policy itself, so the policy can be trained straight from the preference pairs with a single supervised-style loss, with no separate reward model and no online RL sampling loop
  2. It still trains a full separate reward model on the same preference pairs exactly as standard RLHF does, but then applies that reward model's scores using a closed-form policy update instead of running PPO
  3. It discards the human preference-pair data entirely and instead generates all of its training signal by having the model critique its own sampled outputs against a written set of principles
  4. It keeps the standard RLHF pipeline completely intact, including the separate reward model and the full PPO optimization loop, and only changes the architecture of the reward model from a scalar head to a pairwise classifier
Next card → Shuffle