RLHF (reinforcement learning from human feedback): definition

RLHF is a training method where people rank a model’s outputs and the model is tuned toward the preferred ones, which is a big part of why modern assistants are helpful and well-behaved.

After a model learns language from raw text, RLHF teaches it judgement: humans compare its answers, and the model is nudged toward the ones people prefer. It is how a raw text-predictor becomes a helpful, polite assistant that follows instructions.

For a business the takeaway is that model behaviour is shaped, not just trained, which is why different models "feel" different and why the right model for a task is partly a question of temperament.

Related terms

Fine-tuning: Fine-tuning is further training a base model on your own examples so it learns a specific style, format, or task more reliably than prompting alone can achieve.
Large language model (LLM): A large language model is a neural network trained on huge amounts of text to predict the next token, which lets it write, summarise, classify, and answer questions across almost any topic.
Evaluation (evals): An evaluation, or eval, is a repeatable test that measures how well an AI system does its job on real examples, so you can tell whether a change made it better or worse.