A boutique law firm wants a Foundry-deployed model to draft client emails in a very particular tone, but they only have eight example emails written in that style. They ask whether to fine-tune a model on this data before deploying it. What is the best guidance?
Select an answer to reveal the explanation.
Short Explanation
Eight sample emails is a tiny amount of data, and handing that little material to a fine-tuning job usually just teaches the model to memorize the quirks of those eight messages rather than the general style behind them. A much more reliable move with so little material is to drop those same examples straight into the prompt every time so the model can see the pattern and imitate it on the spot, no training required. Saying tone cannot be taught at all misses the point, since matching a writing style from examples is exactly the kind of thing language models are good at when given enough to go on. And retraining the piece that handles finding related documents rather than the piece that writes the emails would not touch the wording style at all, since that is a completely different job inside the system.
Full Explanation
The correct answer is C. With only eight example emails, there is not enough labeled data to fine-tune a custom model reliably; a small dataset like this risks the model overfitting to quirks of those specific examples rather than learning the general tone. Including the same eight emails directly in the prompt as few-shot examples lets the base model pattern-match the desired style at inference time without any training step, which is well suited to small sample sizes. Option A is incorrect because fine-tuning on so few examples typically produces an unstable or overfit model rather than a genuine quality improvement. Option B is incorrect because tone and style are exactly the kind of pattern a language model can pick up from examples, whether through few-shot prompting or fine-tuning with enough data; the premise that it cannot be taught is false. Option D is incorrect because it fine-tunes the wrong component: the embedding model is used for retrieval and similarity search, not for generating the styled email text, so tuning it would not change how the emails are written.