What does “Instruction Tuning” mean?

Continuing training on domain-specific data to adapt a pre-trained model to a specific task.

A parameter-efficient fine-tuning method that adds low-rank adapter matrices.

Methods that adapt models by training a small subset of added parameters.

A high-priority instruction that sets behavior, policy, and response style for a model.

Applying knowledge learned in one task or domain to improve another task.

Additional inference computation used during response generation to improve quality or reasoning.