Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models
This addresses the challenge of high-quality prompt generation for reasoning tasks in AI, offering a scalable solution to reduce manual effort, though it is incremental as it builds on existing chain-of-thought methods.
The paper tackles the problem of costly manual creation of chain-of-thought demonstrations for large language models by introducing Synthetic prompting, which generates and selects effective examples automatically, resulting in outperformance over existing prompting techniques on numerical, symbolic, and algorithmic reasoning tasks.
Large language models can perform various reasoning tasks by using chain-of-thought prompting, which guides them to find answers through step-by-step demonstrations. However, the quality of the prompts depends on the demonstrations given to the models, and creating many of them by hand is costly. We introduce Synthetic prompting, a method that leverages a few handcrafted examples to prompt the model to generate more examples by itself, and selects effective demonstrations to elicit better reasoning. Our method alternates between a backward and forward process to generate new examples. The backward process generates a question that match a sampled reasoning chain, so that the question is solvable and clear. The forward process produces a more detailed reasoning chain for the question, improving the quality of the example. We evaluate our method on numerical, symbolic, and algorithmic reasoning tasks, and show that it outperforms existing prompting techniques.