Preference optimization
Training that favors outputs ranked above alternatives by humans or another model.
What Preference optimization does not show
It changes response tendencies; it does not make the preferred response factually correct.
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 · Supervised fine-tuning · Instruction tuning · RLHF · 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 Preference optimization
What is Preference optimization?
Training that favors outputs ranked above alternatives by humans or another model.
What does Preference optimization not show or guarantee?
It changes response tendencies; it does not make the preferred response factually correct.
Which area of the glossary does Preference optimization 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.
← RLHF · Knowledge distillation →
See it in the full glossary · 751 terms across 19 areas.