Alignment
Post-training methods that steer model behavior toward preferred responses, policies, or safety goals.
Training
Model
Concept
- On-policy training
Learning from examples or trajectories produced by the model or agent policy that is currently being updated.
- Synthetic Data
Training material produced or transformed by one model to teach another, distinct from raw web corpora collected for pretraining or demonstrations written directly by people.
Blog
Training
- Direct Preference Optimization
A preference-optimization training regime that teaches a model from preferred versus rejected answer pairs without fitting a separate reward model and PPO loop first.
- Group Relative Policy Optimization
A groupwise alignment training regime that samples multiple candidate answers for the same prompt and updates the model from how those answers rank relative to one another.
- Instruction Tuning
A supervised post-training regime that teaches a model to follow user instructions by training on prompts paired with desired answers.
- Post-Training
The training stages after base pretraining that reshape how a language model behaves in use, including instruction following, preference alignment, and safety shaping before deployment.
- Proximal Policy Optimization
A post-training regime that updates a model with clipped reinforcement-learning steps so RLHF behavior improves without each update moving too far at once.
- Reinforcement Learning from Human Feedback
A post-training alignment workflow that collects human preference signals, fits a reward model, and optimizes the language-model policy toward preferred behavior.
- Reinforcement Learning with Verifiable Rewards
A post-training reinforcement learning regime where rewards come from externally checkable task outcomes rather than human preference labels alone.
- Supervised Fine-Tuning
A post-training regime that adapts a capable base model by training on labeled input-output examples.