PassDrill Free practice questions with explanations that actually teach.

AI-ENGINEERING · prompting · Q008 · medium

Wang et al. (2022), "Self-Consistency Improves Chain of Thought Reasoning in Language Models," propose replacing greedy decoding with what alternative decoding strategy for chain-of-thought prompts?

  1. Sample multiple diverse reasoning paths for the same question at a nonzero temperature, then take a majority vote over the final answers each path arrives at
  2. Always generate exactly one reasoning path deterministically, then ask a separate human reviewer to check it before accepting the answer
  3. Fine-tune the model on the correct chain-of-thought path found by brute-force search over the entire training set
  4. Discard chain-of-thought reasoning entirely and instead retrieve the answer from an external search engine