A researcher provides the exact same simple instruction—'Summarize the provided article about renewable energy in three sentences'—to two different text-generating AI systems. System X is a model with a few hundred million parameters, developed several years ago. System Y is a modern model with hundreds of billions of parameters. Based on the relationship between model scale and the power of instruction-following, what is the most likely outcome?
0
1
Tags
Ch.4 Alignment - 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
A researcher provides the exact same simple instruction—'Summarize the provided article about renewable energy in three sentences'—to two different text-generating AI systems. System X is a model with a few hundred million parameters, developed several years ago. System Y is a modern model with hundreds of billions of parameters. Based on the relationship between model scale and the power of instruction-following, what is the most likely outcome?
Evaluating the Impact of Model Scale on Instruction Following
The Emergence of Instruction-Following at Scale