Supervised fine-tuning
Fine-tuning on examples pairing inputs with desired outputs.
What Supervised fine-tuning does not show
It teaches demonstrated patterns and may fail when production requests differ materially from the examples.
Terms this definition uses
Related terms in Models and generation
How a model produces text, what its training and decoding controls change, and what none of them can prove about a source.
Autoregressive model · Transformer · Attention · Self-attention · Parameter · Inference · Pretraining · Fine-tuning · Instruction tuning · RLHF · Preference optimization · Knowledge distillation · Quantization · Mixture of experts · Multimodal model · Vision-language model · Small language model · Tokenizer · Temperature · Top-p sampling · Deterministic decoding · System prompt · Developer message · Tool call · Function calling · Structured output · Constrained decoding · Chain of thought · Reasoning trace · Context caching · Context compaction · Model routing · Model drift · Model version
Questions about Supervised fine-tuning
What is Supervised fine-tuning?
Fine-tuning on examples pairing inputs with desired outputs.
What does Supervised fine-tuning not show or guarantee?
It teaches demonstrated patterns and may fail when production requests differ materially from the examples.
Which area of the glossary does Supervised fine-tuning belong to?
Models and generation: How a model produces text, what its training and decoding controls change, and what none of them can prove about a source.
← Fine-tuning · Instruction tuning →
See it in the full glossary · 731 terms across 19 areas.