Exhibit 6.4
4Instruction tuning
With examples of instructions and high-quality answers, the model is trained to follow requests and behave more like an assistant.
Why it is in the museum
A modern language model does not appear fully formed. It passes through data collection, training, adaptation, evaluation and, finally, answer generation.
What supports this exhibit
Primary research paper
Supervised instruction tuning with human-written demonstrations before RLHF.
Main source: Ouyang, L. et al. (2022), InstructGPT.
What to keep in mind: Primary source for one important family of techniques.
Ask the exhibit
This small guide uses only the information documented on this exhibit page. If your question goes beyond that evidence, it will say so instead of inventing an answer.
Start with one of the suggested questions above, or type your own.