Open-domain Question Answering (QA) has garnered substantial interest by combining the advantages of faithfully retrieved passages and relevant passages generated through Large Language Models (LLMs). However, there is a lack of definitive labels available to pair these sources of knowledge. In order to address this issue, we propose an unsupervised and simple framework called Bi-Reranking for Merging Generated and Retrieved Knowledge (BRMGR), which utilizes re-ranking methods for both retrieved passages and LLM-generated passages. We pair the two types of passages using two separate re-ranking methods and then combine them through greedy matching. We demonstrate that BRMGR is equivalent to employing a bipartite matching loss when assigning each retrieved passage with a corresponding LLM-generated passage. The application of our model yielded experimental results from three datasets, improving their performance by +1.7 and +1.6 on NQ and WebQ datasets, respectively, and obtaining comparable result on TriviaQA dataset when compared to competitive baselines.
@article{arxiv.2412.18800,
title = {Improving Generated and Retrieved Knowledge Combination Through Zero-shot Generation},
author = {Xinkai Du and Quanjie Han and Chao Lv and Yan Liu and Yalin Sun and Hao Shu and Hongbo Shan and Maosong Sun},
journal= {arXiv preprint arXiv:2412.18800},
year = {2024}
}