Combining Small and Large Models
Another key approach to utilizing small models involves combining them with large models, typically during the inference stage or deployment, rather than just during training. This approach focuses on architectural or operational combinations to leverage the strengths of both model sizes. Common methods include aggregating the predictions of multiple small models to simulate the performance of a single strong model, and cascading models, where an input is first processed by a small, computationally cheap model and only passed to a larger model if necessary.
0
1
Tags
Foundations of Large Language Models
Ch.4 Alignment - Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Example of Successful Weak-to-Strong Generalization: GPT-4 with GPT-2 Supervision
Weak Performance (Pweak) as a Baseline Metric
Weak-to-Strong Performance (Pweak→strong)
Strong Ceiling Performance (Pceiling)
Performance Gap Recovered (PGR)
Data Selection and Filtering Using Weak Models
Cascading Inference
Weak-to-Strong Generalization via Fine-Tuning on Weak Model Data
AI System Optimization Strategy
An AI development team is building a system to answer a very high volume of customer support queries. They implement a two-step process: first, a small, fast model attempts to answer each query. If this model's confidence in its answer is low, the query is then passed to a much larger, more powerful, but slower model. What is the most significant strategic advantage of this architectural choice?
Direct Supervision via Knowledge Distillation Loss in Weak-to-Strong Generalization
When a large, powerful computational model is trained using labels generated exclusively by a smaller, less accurate model, the performance of the large model on new, unseen data is fundamentally limited and cannot exceed the accuracy of the smaller model that provided the training labels.
Using Small Models for Pre-training or Fine-Tuning
Combining Small and Large Models