In question answering requiring common sense, language models (e.g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work, we finetune smaller language models to generate useful intermediate context, referred to here as elaborations. Our framework alternates between updating two language models -- an elaboration generator and an answer predictor -- allowing each to influence the other. Using less than 0.5% of the parameters of GPT-3, our model outperforms alternatives with similar sizes and closes the gap on GPT-3 on four commonsense question answering benchmarks. Human evaluations show that the quality of the generated elaborations is high.

翻译：在需要常识的问答任务中，语言模型（例如GPT-3）已被用于生成表达背景知识的文本，从而提升性能。然而，使用此类模型的成本极高；在本工作中，我们对较小的语言模型进行微调，使其生成有用的中间上下文，本文称之为“细化”。我们的框架交替更新两个语言模型——一个细化生成器和一个答案预测器——使它们能够相互影响。使用不到GPT-3参数量的0.5%，我们的模型在性能上优于同类规模的其他模型，并在四个常识问答基准测试中缩小了与GPT-3的差距。人工评估表明，生成的细化质量较高。