Prompt-based Conservation Learning for Multi-hop Question Answering. (arXiv:2209.06923v1 [cs.CL])

Multi-hop question answering (QA) requires reasoning over multiple documents
to answer a complex question and provide interpretable supporting evidence.
However, providing supporting evidence is not enough to demonstrate that a
model has performed the desired reasoning to reach the correct answer. Most
existing multi-hop QA methods fail to answer a large fraction of sub-questions,
even if their parent questions are answered correctly. In this paper, we
propose the Prompt-based Conservation Learning (PCL) framework for multi-hop
QA, which acquires new knowledge …

arxiv conservation question answering