PassDrill Free practice questions with explanations that actually teach.

AI-ENGINEERING · prompting · Q009 · medium

Zhou et al. (2022), "Least-to-Most Prompting Enables Complex Reasoning in Large Language Models," describe a two-stage strategy for solving problems harder than those shown in the prompt's examples. What is that strategy?

  1. First prompt the model to decompose the problem into a sequence of simpler subproblems, then sequentially prompt it to solve each subproblem in order, feeding each prior subproblem's answer into the context used for the next
  2. First fine-tune the model on the hardest available examples, then evaluate it zero-shot on easier examples to measure generalization downward
  3. First ask the model to guess the final answer directly, then ask it to generate a chain-of-thought justification for that already-chosen answer after the fact
  4. First run the same prompt through several different LLMs from different vendors, then pick whichever vendor's answer appears most frequently