passdrill
AI & LLM Engineering · Prompt Engineering · Card 037/039 medium

A model asked to write a short biographical paragraph about a real historical figure produces a mostly accurate response but invents two incorrect dates. Dhuliawala et al. (2023), "Chain-of-Verification Reduces Hallucination in Large Language Models," propose a four-step prompting procedure (CoVe) meant to catch this kind of error before the response is delivered to the user. What are the four steps, in order?

  1. Draft an answer, then immediately ask the model to rate its own confidence on a 1-10 scale, then deliver whichever draft scores highest without any further steps
  2. Draft an initial response, plan a set of targeted verification questions that would fact-check specific claims in that draft, answer each verification question independently so those answers are not biased by the original draft, then use the verification answers to produce a final, revised response
  3. Draft an answer, translate it into a different language and back, compare the two versions for discrepancies, and keep whichever version is shorter
  4. Draft an answer, retrieve external documents matching every named entity in the draft, replace every named entity with whatever the retrieved documents say without any further verification step, and stop
Next card → Shuffle