# RLHF (Reinforcement Learning from Human Feedback)

> RLHF trains a model against human preferences: people rank outputs, a reward model learns the ranking, and the LLM is optimized to produce preferred responses.

RLHF shapes behavior rather than knowledge: humans rank candidate outputs, a reward model learns those rankings, and the LLM is optimized by reinforcement learning to score highly against it. It is what turned text predictors into assistants, and it rewards what raters prefer, which is where sycophancy comes from.

**RLHF (reinforcement learning from human feedback) is the post-training technique that aligns a model with human preferences: humans rank candidate outputs, a reward model learns those rankings, and the LLM is optimized — via reinforcement learning — to score highly.**

It's the stage that made modern assistants possible: pretraining teaches language and knowledge; RLHF teaches *behavior* — follow instructions, be helpful, refuse harm, format sanely. The classic pipeline (preference data → reward model → PPO optimization) is heavyweight, which spawned a family of successors: [DPO](/glossary/dpo) optimizes on preferences directly without a separate reward model; RLAIF and [Constitutional AI](/glossary/constitutional-ai) substitute AI feedback guided by principles for armies of human raters; and the [reasoning-model](/glossary/reasoning-model) era extended RL beyond preferences to *verifiable rewards* (did the math check out, did the code pass) — arguably the most consequential RL development since.

For practitioners the takeaway is interpretive: model quirks like sycophancy and over-hedging are RLHF artifacts — the model optimizing for approval — worth remembering when [designing evals](/guides/evaluation/write-llm-evals) that measure truth rather than likability.

---

_Source: https://agentscamp.com/glossary/rlhf — Term on AgentsCamp._
