passdrill
AI & LLM Engineering · Prompt Engineering · Card 015/024 hard

Min et al. (2022), "Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?," test in-context learning by randomly replacing the labels in few-shot demonstrations with incorrect ones. What did they find, and what does it suggest about why few-shot demonstrations help?

  1. Replacing the labels with random ones caused accuracy to collapse to chance level on every task tested, confirming that the model learns the exact input-label mapping shown in the demonstrations the way a supervised classifier would
  2. Replacing the labels with random ones improved accuracy beyond using correct labels, showing that few-shot demonstrations actively mislead the model and should generally be avoided
  3. The experiment could not be run, because in-context learning requires every demonstration label to be verified against a held-out validation set before each query
  4. Replacing the demonstrations' labels with random, often-incorrect ones barely hurt accuracy across a range of classification and multiple-choice tasks, suggesting that the correctness of the input-label mapping matters far less than other aspects of the demonstrations, such as the label space, the input distribution, and the overall format
Next card → Shuffle