What is a soft prompt tuning?
A technique for tuning a large language model for a particular task, without resource intensive fine-tuning.
soft prompt tuning explained in plain English
A technique for tuning a large language model for a particular task, without resource intensive fine-tuning. Instead of retraining all the weights in the model, soft prompt tuning automatically adjusts a prompt to achieve the same goal. Given a textual prompt, soft prompt tuning typically appends additional token embeddings to the prompt and uses backpropagation to optimize the input. A "hard" prompt contains actual tokens instead of token embeddings.
Example
Practitioners refer to soft prompt tuning when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- Attention
A mechanism that lets a model focus on the most relevant parts of its input when producing an output, weighting what matters most in context.
- auto-regressive model
A model that infers a prediction based on its own previous predictions.
- autoencoder
A system that learns to extract the most important information from the input.
- average precision at k
A metric for summarizing a model's performance on a single prompt that generates ranked results, such as a numbered list of book recommendations.
- black box model
A model whose "reasoning" is impossible or difficult for humans to understand.
- Chain-of-Thought Prompting
Asking an AI to show its reasoning step by step before giving a final answer, which often improves accuracy on complex tasks.
- conversational coding
An iterative dialog between you and a generative AI model for the purpose of creating software.
- depth
The sum of the following in a neural network: - the number of hidden layers - the number of output layers, which is typically 1 - the number of any embedding layers For example, a neural network with five hidden layers and one output layer has a depth of 6.
- deterministic
A system that always returns the same output for a given input.
- direct prompting
Synonym for zero-shot prompting.