Meta Chain-of-Thought Prompting (Meta-CoT)
First page
Paper summary
A generalizable CoT framework that selects domain-appropriate reasoning patterns for the task at hand.
Ask this paper
01
Task-adaptive CoT: Rather than using a fixed CoT prompt template, Meta-CoT adaptively selects reasoning patterns based on task characteristics.
02
Pattern library: Maintains a library of reasoning templates tailored to task families (math, logic, commonsense, etc.), picking the best one per query.
03
Strong across tasks: Improves reasoning accuracy across diverse task types compared to single-template CoT prompting.
04
Generalizable framework: The Meta-CoT pattern is easy to extend to new task families by just adding new templates to the library.