Elaboration-Generating Commonsense Question Answering at Scale (2209.01232v2)

Abstract: In question answering requiring common sense, LLMs (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 LLMs to generate useful intermediate context, referred to here as elaborations. Our framework alternates between updating two LLMs -- 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.