# Prompt tuning

**Source:** https://promtable.com/glossary/prompt-tuning

> Prompt tuning trains a small set of "soft prompt" tokens — continuous vectors that prepend to the model input — to specialise a frozen LLM for a task with minimal parameters.

---
Prompt tuning trains a small set of "soft prompt" tokens — continuous vectors that prepend to the model input — to specialise a frozen LLM for a task with minimal parameters.

Introduced by Lester et al. (2021), prompt tuning learns task-specific embedding vectors (not text) that get prepended to the model's input. Only the soft prompt parameters train; the rest of the model is frozen. Variants include prefix tuning (per-layer soft prompts) and P-tuning v2 (soft prompts at multiple layers). For narrow tasks with enough labelled data, prompt tuning can approach full fine-tuning quality at a tiny fraction of trainable parameters. Less popular in 2026 than LoRA for most use cases — LoRA is more flexible — but prompt tuning still wins on truly parameter-constrained deployments.

## When to use

- Highly parameter-constrained deployments.
- Narrow tasks with sufficient labelled data.

## Common mistakes

- Trying to learn complex multi-task behaviour with a small soft prompt — usually under-fits.
- Mixing soft prompts and few-shot examples without thinking about token budget impact.

## Related terms

- [fine-tuning](https://promtable.com/glossary/fine-tuning)
- [lora](https://promtable.com/glossary/lora)
- [few-shot-prompting](https://promtable.com/glossary/few-shot-prompting)

## Sources

- [Lester et al. 2021 (arXiv)](https://arxiv.org/abs/2104.08691)

*Last updated: 2026-06-01*
---

Original page: https://promtable.com/glossary/prompt-tuning
Maintained by Promtable (https://promtable.com). Content: CC BY 4.0. Cite as "Promtable — https://promtable.com/glossary/prompt-tuning".
Contact: info@vibecodingturkey.com.