Reinforcement learning from human feedback
Training a model with rewards learned from people's comparisons of its answers, the method that made ChatGPT helpful.
Also: RLHF
In RLHF, people compare pairs of model answers and say which is better. A reward model is trained to predict those choices, and the language model is then trained with reinforcement learning, often the PPO method, to produce answers the reward model scores highly, while a penalty keeps it close to its starting point. The approach was developed by OpenAI and DeepMind researchers from 2017 and applied to language in InstructGPT in 2022. It made models more helpful and polite, but can also make them flattering or overconfident.
See also
Find models that mention Reinforcement learning from human feedback