mlsanityData to 7 Oct 2026

Answering Complex Open-Domain Questions with Multi-Hop Dense Retrieval

arXiv 2009.12756 ↗First posted 27 Sep 2020cs.CLcited by 160

Not on the map. Why?

Cited by 36 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose a simple and efficient multi-hop dense retrieval approach for answering complex open-domain questions, which achieves state-of-the-art performance on two multi-hop datasets, HotpotQA and multi-evidence FEVER. Contrary to previous work, our method does not require access to any corpus-specific information, such as inter-document hyperlinks or human-annotated entity markers, and can be applied to any unstructured text corpus. Our system also yields a much better efficiency-accuracy trade-off, matching the best published accuracy on HotpotQA while being 10 times faster at inference time.

Key facts. Cited by 160 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 30; 2023: 26; 2024: 28; 2025: 23; 2026: 28.

160 papers.

Sort:

By area:

  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  2. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  3. 2022Demonstrate-Search-Predict: Composing retrieval and language models for knowledge-intensive NLPcited by 316
  4. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  5. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  6. 2021RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-rankingcited by 175
  7. 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 170
  8. 2023Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answeringcited by 150
  9. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  10. 2022Internet-augmented language models through few-shot prompting for open-domain question answeringcited by 131
  11. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
  12. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
38 more
  1. 2021Adaptive Semiparametric Language Modelscited by 83
  2. 2022DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Basescited by 83
  3. 2024NV-Retriever: Improving text embedding models with effective hard-negative miningcited by 83
  4. 2022Iteratively Prompt Pre-trained Language Models for Chain of Thoughtcited by 75
  5. 2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
  6. 2021MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documentscited by 53
  7. 2021PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrievalcited by 50
  8. 2021Joint Passage Ranking for Diverse Multi-Answer Retrievalcited by 43
  9. 2023EX-FEVER: A Dataset for Multi-hop Explainable Fact Verificationcited by 36
  10. 2023Merging Generated and Retrieved Knowledge for Open-Domain QAcited by 36
  11. 2023End-to-End Beam Retrieval for Multi-Hop Question Answeringcited by 35
  12. 2022Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Modelcited by 32
  13. 2021Conversational Question Answering: A Surveycited by 31
  14. 2021Adaptive Information Seeking for Open-Domain Question Answeringcited by 29
  15. 2023Towards Possibilities & Impossibilities of AI-generated Text Detection: A Surveycited by 28
  16. 2024Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sourcescited by 27
  17. 2022Entailment Tree Explanations via Iterative Retrieval-Generation Reasonercited by 26
  18. 2021Multi-Step Reasoning Over Unstructured Text with Beam Dense Retrievalcited by 25
  19. 2021Geographic Question Answering: Challenges, Uniqueness, Classification, and Future Directionscited by 24
  20. 2024Privacy Preserving Prompt Engineering: A Surveycited by 24
  21. 2022Visconde: Multi-document QA with GPT-3 and Neural Rerankingcited by 23
  22. 2025PropRAG: Guiding Retrieval with Beam Search over Proposition Pathscited by 22
  23. 2022Reasoning over Public and Private Data in Retrieval-Based Systemscited by 21
  24. 2022Modeling Multi-hop Question Answering as Single Sequence Predictioncited by 21
  25. 2021Database Reasoning Over Textcited by 20
  26. 2024MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledgecited by 20
  27. 2025Supervising the search process produces reliable and generalizable information-seeking agentscited by 20
  28. 2021Boosting Search Engines with Interactive Agentscited by 19
  29. 2022Augmenting Pre-trained Language Models with QA-Memory for Open-Domain Question Answeringcited by 19
  30. 2022Few-shot Reranking for Multi-hop QA via Language Model Promptingcited by 19
  31. 2023Chain-of-Skills: A Configurable Model for Open-domain Question Answeringcited by 19
  32. 2021Hybrid Autoregressive Inference for Scalable Multi-hop Explanation Regenerationcited by 17
  33. 2022Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQAcited by 17
  34. 2024Grounding by Trying: LLMs with Reinforcement Learning-Enhanced Retrievalcited by 17
  35. 2023Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understandingcited by 16
  36. 2024REAPER: Reasoning based Retrieval Planning for Complex RAG Systemscited by 16
  37. 2021Exploiting Reasoning Chains for Multi-hop Science Question Answeringcited by 15
  38. 2022Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledgecited by 14

50 most cited of 160 All 160 (JSON)