Comparing Model Adaptation Strategies
A development team is creating a tool to categorize customer feedback emails into 'Bug Report', 'Feature Request', or 'General Inquiry'. They are considering two strategies:
- Using a general-purpose model with a detailed, multi-part prompt that provides clear instructions and examples for each category.
- Investing time and resources to fine-tune a model on thousands of labeled examples, which would allow it to perform the same task using a much shorter, simpler prompt.
Analyze these two approaches by identifying one key advantage and one key disadvantage of the fine-tuning strategy (Strategy 2) compared to the detailed prompting strategy (Strategy 1).
0
1
Tags
Ch.3 Prompting - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Optimizing a Text-to-SQL Service
A company develops a service that summarizes legal documents. The structure of these documents and the key information to be extracted are highly standardized and have not changed in years. To optimize their process, they are considering a significant one-time investment to fine-tune their Large Language Model on tens of thousands of examples. The goal is to enable the model to produce accurate summaries using very minimal, one-sentence prompts instead of the complex, multi-part prompts they currently use. Which of the following statements best evaluates the suitability of this fine-tuning strategy for their specific situation?
Comparing Model Adaptation Strategies