passdrill
AI & LLM Engineering · Prompt Engineering · Card 035/039 medium

Chia et al. (2023), "Contrastive Chain-of-Thought Prompting," start from a surprising finding in prior work: giving a model chain-of-thought demonstrations with deliberately invalid reasoning had only a small negative effect compared to fully valid demonstrations, suggesting standard CoT does not clearly teach the model what mistakes to avoid. What do the authors propose instead, and what is its rationale?

  1. Removing chain-of-thought demonstrations altogether and relying solely on zero-shot instructions, on the theory that any demonstration risks teaching a spurious pattern
  2. Providing both valid and invalid reasoning demonstrations side by side for the same or paired problems, together with an automatic method for constructing such contrastive demonstrations, so the model is explicitly shown examples of flawed reasoning alongside correct reasoning rather than only ever seeing correct chains
  3. Increasing the number of valid chain-of-thought demonstrations from a handful to several dozen, so that sheer repetition overwhelms any influence from invalid reasoning
  4. Replacing human-written demonstrations with demonstrations generated entirely by a separate, larger teacher model, without regard to whether the reasoning in them is valid or invalid
Next card → Shuffle