Soft prompting (e.g., prompt tuning) involves adding trainable parameters (soft prompts) to an LLM’s input while keeping the model’s weights frozen, adapting it to tasks without task-specific retraining. This is efficient when fine-tuning or large datasets aren’t feasible, making Option C correct. Option A suits full fine-tuning, not soft prompting, which avoids extensive labeled data needs. Option B could apply, but domain adaptation often requires more than soft prompting (e.g., fine-tuning). Option D describes continued pretraining, not soft prompting. Soft prompting excels in low-resource customization.
OCI 2025 Generative AI documentation likely discusses soft prompting under parameter-efficient methods.
Contribute your Thoughts:
Chosen Answer:
This is a voting comment (?). You can switch to a simple comment. It is better to Upvote an existing comment if you don't have anything to add.
Submit