Multi-Hop Question Answering (MHQA) tasks present a significant challenge for large language models (LLMs) due to the intensive knowledge required. Current solutions, like Retrieval-Augmented Generation, typically retrieve potential documents from an external corpus to read an answer. However, the performance of this retrieve-then-read paradigm is constrained by the retriever and the inevitable noise in the retrieved documents. To mitigate these challenges, we introduce a novel generate-then-ground (GenGround) framework, synergizing the parametric knowledge of LLMs and external documents to solve a multi-hop question. GenGround empowers LLMs to alternate two phases until the final answer is derived: (1) formulate a simpler, single-hop question and directly generate the answer; (2) ground the question-answer pair in retrieved documents, amending any wrong predictions in the answer. We also propose an instructional grounding distillation method to generalize our method into smaller models. Extensive experiments conducted on four datasets illustrate the superiority of our method.

翻译：多跳问答任务因所需知识密集而对大型语言模型构成显著挑战。当前解决方案，如检索增强生成，通常从外部语料库检索潜在文档以读取答案。然而，这种"检索-阅读"范式的性能受限于检索器以及检索文档中不可避免的噪声。为缓解这些挑战，我们引入了一种新颖的生成后接地框架，协同利用LLMs的参数化知识和外部文档来解决多跳问题。该框架使LLMs能够交替执行两个阶段直至推导出最终答案：(1) 制定一个更简单的单跳问题并直接生成答案；(2) 将问答对基于检索文档进行接地，修正答案中的错误预测。我们还提出了一种指令式接地蒸馏方法，将我们的方法推广至更小模型。在四个数据集上进行的大量实验证明了我们方法的优越性。