What is prompt tuning in the context of watsonx.ai and watsonx Assistant?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Todd Lammle: 'Imagine you're building a chatbot and this exact situation comes up — fine-tuning soft prompt tokens to adapt a foundation model to a specific task without changing model weights is your go-to move. Prompt tuning learns a small set of soft prompt tokens prepended to model input to steer its behavior for a specific task while keeping the underlying model weights frozen. This is a classic Domain 4: Integrate with watsonx concept you'll want locked in before exam day.'
Full explanation below image
Full Explanation
Prompt tuning learns a small set of soft prompt tokens prepended to model input to steer its behavior for a specific task while keeping the underlying model weights frozen. It is not full model training; NLU training data adjustment; or OpenAPI modification. The correct answer, "Fine-tuning soft prompt tokens to adapt a foundation model to a specific task without changing model weights", directly satisfies the scenario because it aligns with watsonx Assistant's design principles and the specific capability being tested. The incorrect options ("Training a full new language model from scratch for the assistant", "Adjusting the watsonx Assistant NLU training data prompts", "Rewriting the OpenAPI specification to include LLM parameters") may appear relevant but each misses a key requirement or introduces a step that is either unnecessary or belongs to a different workflow. Mastering the distinction between these approaches is essential for effective watsonx Assistant implementations and is a core focus of the Domain 4: Integrate with watsonx section of the certification exam.