Elaboration-Generating Commonsense Question Answering at Scale
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.
Code (1)
Tasks
Common Sense ReasoningQuestion AnsweringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generated Knowledge Prompting for Commonsense Reasoning
It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated know…
Language ModelingLanguage ModellingOpen-Ended Question AnsweringGenerated Knowledge Prompting for Commonsense Reasoning
It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated know…
Language ModelingLanguage ModellingOpen-Ended Question AnsweringChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models
Large language models (LLMs) have made significant progress in NLP. However, their ability to memorize, represent, and leverage commonsense knowledge has been a well-known pain point. In this paper, we specifically focus…
Instruction FollowingArT: All-round Thinker for Unsupervised Commonsense Question-Answering
Without labeled question-answer pairs for necessary training, unsupervised commonsense question-answering (QA) appears to be extremely challenging due to its indispensable unique prerequisite on commonsense source like k…
AllQuestion AnsweringArT: All-round Thinker for Unsupervised Commonsense Question Answering
Without labeled question-answer pairs for necessary training, unsupervised commonsense question-answering (QA) appears to be extremely challenging due to its indispensable unique prerequisite on commonsense source like k…
AllQuestion Answering