Explaining the Impact of Targeted Training
A large language model is pre-trained on a vast corpus of text, including countless recipes. However, when prompted with 'Give me a recipe for chocolate chip cookies,' it produces a rambling, unstructured text that mixes ingredients, steps, and baking history. After being trained on just 1,000 examples of well-structured recipes, it consistently generates clear, step-by-step instructions. Based on the principle of how this secondary training works, explain this significant improvement despite the small size of the training dataset.
0
1
Tags
Ch.2 Generative Models - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Ch.4 Alignment - Foundations of Large Language Models
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Fine-Tuning Pre-trained Models for Downstream Tasks
Instruction Fine-Tuning
Superficial Alignment Hypothesis
Challenge of Opaque Pre-Training Data in Fine-Tuning
A team develops a large language model pre-trained on a massive, diverse corpus of text from the internet. When initially tested on the task of generating concise summaries of legal documents, its performance is poor and unstructured. The team then collects a small, curated dataset of 500 legal documents and their corresponding expert-written summaries. After training the model on this small dataset, its ability to summarize new legal documents improves dramatically. Which statement best analyzes the role of this second training phase?
Critiquing a Model Training Hypothesis
Implicit Learning of Instruction-Response Mappings During Pre-training
Explaining the Impact of Targeted Training