Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering

arXiv (Cornell University)

Abstract

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.

Authors 6

1. Zhengliang Shi

   Shandong University

   Affiliation as printed

   Shandong University , Qingdao , China

2. Weiwei Sun

   Shandong University

   Affiliation as printed

   Shandong University , Qingdao , China

3. Shen Gao

   University of Electronic Science and Technology of China

   Affiliation as printed

   University of Electronic Science and Technology of China , Chengdu , China

4. Pengjie Ren

   Shandong University

   Affiliation as printed

   Shandong University , Qingdao , China

5. Zhumin Chen

   Shandong University

   Affiliation as printed

   Shandong University , Qingdao , China

6. Zhaochun Ren Aachen

   Leiden University

   Affiliation as printed

   Leiden University , Leiden , The Netherlands