passdrill
AI & LLM Engineering · Prompt Engineering · Card 019/024 medium

Press et al. (2022), "Measuring and Narrowing the Compositionality Gap in Language Models," introduce the "self-ask" prompting method to address multi-hop questions whose sub-answers the model already knows individually but fails to combine correctly. How does self-ask structure the model's output?

  1. The model is asked to answer the multi-hop question directly in a single token with no intermediate text of any kind, which the paper shows eliminates the compositionality gap entirely
  2. Two separate, independently prompted models debate each other's answers over several rounds until they converge on the same final answer, which is the paper's central proposed method
  3. The compositionality gap is closed simply by scaling up model size, and self-ask is presented only as an unrelated historical baseline that the paper argues should be discarded
  4. The prompt's few-shot exemplars teach the model to explicitly decide whether a follow-up question is needed, then pose and answer that follow-up question itself within the same generation, repeating as needed before stating the final answer -- a structure into which an external search engine can optionally be plugged to answer the follow-up questions instead
Next card → Shuffle