MrRank: Improving Question Answering Retrieval System through Multi-Result Ranking Model

TL;DR

This paper introduces MrRank, a multi-result ranking model that combines diverse IR systems using learning-to-rank techniques, significantly improving question answering retrieval performance and achieving state-of-the-art results.

Contribution

It proposes a novel method to effectively combine heterogeneous IR systems for question answering, addressing limitations of prior approaches.

Findings

Significant performance improvement over previous methods

Outperforms existing approaches on ReQA SQuAD

Achieves state-of-the-art results in retrieval QA

Abstract

Large Language Models (LLMs) often struggle with hallucinations and outdated information. To address this, Information Retrieval (IR) systems can be employed to augment LLMs with up-to-date knowledge. However, existing IR techniques contain deficiencies, posing a performance bottleneck. Given the extensive array of IR systems, combining diverse approaches presents a viable strategy. Nevertheless, prior attempts have yielded restricted efficacy. In this work, we propose an approach that leverages learning-to-rank techniques to combine heterogeneous IR systems. We demonstrate the method on two Retrieval Question Answering (ReQA) tasks. Our empirical findings exhibit a significant performance enhancement, outperforming previous approaches and achieving state-of-the-art results on ReQA SQuAD.