Dense Passage Retrieval for Open-Domain Question Answering

Authors: Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih (2020)

arXiv: 2004.04906

Domains

Applications

TLDR (English)

Dual-tower BERT + in-batch negatives trains first industrial-grade dense retriever, virtually eliminating BM25 overnight. Today's vector search (FAISS, pgvector) engineering paradigm solidified here.

TLDR（中文）

双塔 BERT + in-batch negatives 训出第一个工业级稠密检索器，几乎一夜淘汰 BM25。今天向量检索（FAISS、pgvector）的工程范式从这里定型。

Appears in These Articles

• RAG 与检索增强：让模型有外部记忆
• RAG and Retrieval Augmentation: Giving Models External Memory

Co-cited Papers

These papers appear in the same articles as this one

• Improving language models by retrieving from trillions of tokens Sebastian Borgeaud et al. (2022)
• Precise Zero-Shot Dense Retrieval without Relevance Labels Luyu Gao et al. (2022)
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks Patrick Lewis et al. (2020)
• Visual Instruction Tuning Haotian Liu et al. (2023)

Related Papers

Other papers in the same domain

• Model Context Protocol (MCP) Anthropic (2024)
  Applications
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues? Carlos E. Jimenez et al. (2024)
  EvaluationApplications
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering John Yang et al. (2024)
  Applications
• Toolformer: Language Models Can Teach Themselves to Use Tools Timo Schick et al. (2023)
  Applications
• Reflexion: Language Agents with Verbal Reinforcement Learning Noah Shinn et al. (2023)
  Applications
• Efficient Guided Generation for Large Language Models Brandon T. Willard et al. (2023)
  InferenceApplications