Towards Universal Dense Retrieval For Open-domain Question Answering

Abstract

In open-domain question answering, a model receives a text question as input and searches for the correct answer using a large evidence corpus. The retrieval step is especially difficult as typical evidence corpora have \textit\{millions\} of documents, each of which may or may not have the correct answer to the question. Very recently, dense models have replaced sparse methods as the de facto retrieval method. Rather than focusing on lexical overlap to determine similarity, dense methods build an encoding function that captures semantic similarity by learning from a small collection of question-answer or question-context pairs. In this paper, we investigate dense retrieval models in the context of open-domain question answering across different input distributions. To do this, first we introduce an entity-rich question answering dataset constructed from Wikidata facts and demonstrate dense models are unable to generalize to unseen input question distributions. Second, we perform analy

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysciavolino2021towards

Related papers

• Questions Are All You Need To Train A Dense Passage Retriever (2022)10.35
• Webfaq: A Multilingual Collection Of Natural Q&A Datasets For Dense Retrieval (2025)0.00
• Multi-view Document Representation Learning For Open-domain Dense Retrieval (2022)10.21
• QAEA-DR: A Unified Text Augmentation Framework For Dense Retrieval (2024)5.24
• What Are You Token About? Dense Retrieval As Distributions Over The Vocabulary (2022)8.09
• Pre-training Multi-modal Dense Retrievers For Outside-knowledge Visual Question Answering (2023)7.50
• Universal Vision-language Dense Retrieval: Learning A Unified Representation Space For Multi-modal Retrieval (2022)3.45
• Dense Passage Retrieval In Conversational Search (2025)0.00