Least-to-Most Prompting
Also called problem decomposition.
Least-to-most prompting first asks the model to break a complex problem into simpler subproblems, then solves them in order, feeding each answer into the next.
Description
Zhou et al. showed it generalizes to problems harder than those in the examples, a weakness of standard chain-of-thought, with strong results on compositional generalization benchmarks.
Sources
- Zhou et al. (2022). Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.
Cite this entry
Protologue. (2026). Least-to-Most Prompting. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.0.0, PTL-0030). https://protologue.com/t/least-to-most-prompting/
BibTeX
@misc{protologue_least_to_most_prompting,
title = {Least-to-Most Prompting},
author = {{Protologue}},
year = {2026},
howpublished = {Protologue: A Taxonomy of Prompting and LLM Techniques, v1.0.0},
note = {Entry PTL-0030},
url = {https://protologue.com/t/least-to-most-prompting/}
}