Definition. Instruction tuning [wei2022finetuned, Section 2 and Figure 2] [ftip-002B]
Definition. Instruction tuning [wei2022finetuned, Section 2 and Figure 2] [ftip-002B]
Instruction tuning fine-tunes a pretrained language model on a mixture of tasks whose examples are expressed through natural-language instructions and corresponding target outputs. The task description and any input are placed in the prompt; the target output supplies the continuation to be learned.
The construction changes the model parameters by supervised learning. It does not require a learned reward model, preference comparisons, or interaction with an environment.