Primary Source of Out-of-Distribution Generalization: Pre-training vs. Fine-tuning
A key unresolved question in LLM development is whether out-of-distribution generalization is primarily a result of the extensive pre-training phase or the subsequent fine-tuning stage. Understanding the relative contributions of each phase is crucial for optimizing model training and adaptation.
0
1
Tags
Ch.4 Alignment - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Primary Source of Out-of-Distribution Generalization: Pre-training vs. Fine-tuning
Diagnosing Inconsistent Fine-Tuning Performance
A development team is fine-tuning a large, pre-trained language model to act as a specialized legal assistant. They notice that the model quickly masters tasks related to contract law after seeing only a few examples, but struggles to generate accurate summaries of intellectual property case law, even with a large number of fine-tuning examples. What is the most likely underlying reason for this discrepancy?
The 'Unknown Unknowns' of Fine-Tuning Strategy