passdrill
AI & LLM Engineering · Prompt Engineering · Card 038/039 hard

A team wants to steer a large black-box LLM they cannot fine-tune (no access to weights) toward producing summaries that reliably include certain keywords, without hand-crafting a new instruction for every single input document. Li et al. (2023), "Guiding Large Language Models via Directional Stimulus Prompting," propose a framework for exactly this setting. What mechanism does Directional Stimulus Prompting use, and how is that mechanism trained?

  1. It trains a separate, small, tunable policy model (such as a T5-sized model) to generate an instance-specific 'directional stimulus,' a short hint or set of keywords tailored to each input, which is inserted into the prompt sent to the black-box LLM; the policy model itself is optimized via supervised fine-tuning on labeled data and/or reinforcement learning using rewards derived from the black-box LLM's own output quality
  2. It fine-tunes the black-box LLM's own weights directly on a small labeled dataset of ideal summaries, despite the team's lack of weight access, by using a gradient-free zeroth-order optimization method against the model's API
  3. It hard-codes the same fixed list of keywords into every prompt regardless of the input document, relying on the black-box LLM to decide on its own which of the fixed keywords are actually relevant
  4. It relies entirely on the black-box LLM's built-in retrieval-augmented generation feature to pull in relevant keywords from a search index, with no additional model or training step involved
Next card → Shuffle