Teaching Small LMs to Reason
First page
Paper summary
An approach that teaches smaller language models to explicitly select among reasoning techniques for each problem.
Ask this paper
01
Reasoning technique menu: Trains the small LM to choose among step-by-step processing, recall-then-generate, recall-reason-generate, extract-generate, and direct-answer strategies.
02
Technique selection: The model learns when to apply each strategy based on problem structure, not just which answer to produce.
03
Matches 5-10x larger models: Attains zero-shot reasoning performance similar or better than models 5-10x larger on complex reasoning tasks.
04
Practical scaling: Offers a recipe for teams that can't deploy frontier-scale models but need strong reasoning quality - a recurring production constraint.