Dense Passage Retrieval for Open-Domain Question Answering

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

arXiv： 2004.04906

领域

应用

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。

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.

出现在这些文章里

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

同被引用

这些论文与本文出现在同一篇文章中

• 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)

相关论文

同一领域的其他论文

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