Prompt Tuning
Also called soft prompts, soft prompt tuning.
Prompt tuning learns a small set of continuous "soft prompt" embeddings that are prepended to the input, by gradient descent, while keeping the language model's weights frozen.
Description
Lester et al. showed that as models grow, prompt tuning approaches the quality of full fine-tuning while storing only a tiny number of task-specific parameters. Soft prompts are vectors rather than readable text.
Sources
- Lester et al. (2021). The Power of Scale for Parameter-Efficient Prompt Tuning.
Cite this entry
Protologue. (2026). Prompt Tuning. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0076). https://protologue.com/t/prompt-tuning/
BibTeX
@misc{protologue_prompt_tuning,
title = {Prompt Tuning},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0076},
url = {https://protologue.com/t/prompt-tuning/}
}