Generate rather than Retrieve: Large Language Models are Strong Context Generators
https://arxiv.org/abs/2209.10063
ICLR 2023
We call our method generate-then-read (GenRead), which first prompts a large language model to generate contextutal documents based on a given question, and then reads the generated documents to produce the final answer.
既存の手法が retrieve-then-read なのに対して
we propose a novel clustering-based prompting method that selects distinct prompts
https://github.com/wyu97/GenRead
Figure 1: An overall framework of clustering-based prompting method