Improving Passage Retrieval With Zero-shot Question Generation

Abstract

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trained language model to compute the probability of the input question conditioned on a retrieved passage. This approach can be applied on top of any retrieval method (e.g. neural or keyword-based), does not require any domain- or task-specific training (and therefore is expected to generalize better to data distribution shifts), and provides rich cross-attention between query and passage (i.e. it must explain every token in the question). When evaluated on a number of open-domain retrieval datasets, our re-ranker improves strong unsupervised retrieval models by 6%-18% absolute and strong supervised models by up to 12% in terms of top-20 passage retrieval accuracy. We also obtain new state-of-the-art results on full open-domain question answering by simply adding the new r

Stats

• citations51
• S2 citations—
• github stars0
• HF likes0
• heat score12.87
• arxiv keysachan2022improving

Related papers

• Embedding-based Zero-shot Retrieval Through Query Generation (2020)0.00
• Hybrid And Collaborative Passage Reranking (2023)2.26
• Rank-k: Test-time Reasoning For Listwise Reranking (2025)0.00
• Few-shot Prompting For Pairwise Ranking: An Effective Non-parametric Retrieval Model (2024)5.84
• HYRR: Hybrid Infused Reranking For Passage Retrieval (2022)0.00
• If At First You Don't Succeed: Test Time Re-ranking For Zero-shot, Cross-domain Retrieval (2023)0.00
• Efficient Passage Retrieval With Hashing For Open-domain Question Answering (2021)15.77
• Learning To Rank In Generative Retrieval (2023)11.91