Rider: Reader-Guided Passage Reranking for Open-Domain Question Answering

TL;DR

This paper introduces RIDER, a simple, training-free passage reranking method for open-domain QA that significantly improves retrieval accuracy and answer correctness by reranking based on the reader’s top predictions.

Contribution

RIDER is a novel, training-free reranking approach that outperforms supervised rerankers and enhances open-domain QA performance.

Findings

Achieves 10-20% gains in top-1 retrieval accuracy.

Improves EM scores by 1-4 points without retraining.

Outperforms state-of-the-art supervised rerankers.

Abstract

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose a simple and effective passage reranking method, named Reader-guIDEd Reranker (RIDER), which does not involve training and reranks the retrieved passages solely based on the top predictions of the reader before reranking. We show that RIDER, despite its simplicity, achieves 10 to 20 absolute gains in top-1 retrieval accuracy and 1 to 4 Exact Match (EM) gains without refining the retriever or reader. In addition, RIDER, without any training, outperforms state-of-the-art transformer-based supervised rerankers. Remarkably, RIDER achieves 48.3 EM on the Natural Questions dataset and 66.4 EM on the TriviaQA dataset when only 1,024 tokens (7.8 passages on average) are used as the reader input after passage reranking.