passdrill
AI & LLM Engineering · Prompt Engineering · Card 020/024 easy

Zhang et al. (2022), "Automatic Chain of Thought Prompting in Large Language Models," propose Auto-CoT to avoid the manual effort, and potential for hand-written mistakes, involved in writing few-shot chain-of-thought exemplars by hand. What two-step procedure does Auto-CoT use to build its demonstrations automatically?

  1. First, ask human annotators to hand-write a reasoning chain for every single question in the dataset; second, use the model to pick which of those human-written chains looks most fluent
  2. First, cluster the dataset's questions by similarity and pick one representative question from each cluster; second, generate a reasoning chain for each representative question automatically using zero-shot chain-of-thought (for example, "Let's think step by step"), assembling the resulting diverse set of question-plus-generated-chain pairs into the few-shot demonstrations
  3. First, fine-tune the model on a large labeled reasoning dataset; second, discard the few-shot examples entirely, since the fine-tuned model no longer needs any demonstrations
  4. First, generate one reasoning chain for the very first question in the dataset; second, reuse that exact same chain, unmodified, as the only demonstration for every other question regardless of topic
Next card → Shuffle