[2004.04906] Dense Passage Retrieval for Open-Domain Question Answering

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.

Dense Passage Retrieval for Open-Domain Question Answering Vladimir Karpukhin∗, Barlas Oğuz∗, Sewon Min† , Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen‡ , Wen-tau Yih † ‡ Facebook AI University of Washington Princeton University {vladk, barlaso,…

related reading

• [2005.11401] Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasksarxiv.org
• [2212.10496] Precise Zero-Shot Dense Retrieval without Relevance Labelsarxiv.org
• [2002.08909] REALM: Retrieval-Augmented Language Model Pre-Trainingarxiv.org
• [2603.07146] Fine-Grained Table Retrieval Through the Lens of Complex Queriesarxiv.org
• 2502.11089arxiv.org
• [2005.14165] Language Models are Few-Shot Learnersarxiv.org
• [2508.21038] On the Theoretical Limitations of Embedding-Based Retrievalarxiv.org
• On the Theoretical Limitations of Embedding-Based Retrievalarxiv.org
• [1606.03126] Key-Value Memory Networks for Directly Reading Documentsarxiv.org
• [2506.06266] Cartridges: Lightweight and general-purpose long context representations via self-studyarxiv.org
• 2409.02908arxiv.org
• 1810.04805arxiv.org