mlsanityData to 14 Oct 2026

Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering

arXiv 1905.05733 ↗First posted 14 May 2019cs.CL cs.LGcited by 48

Not on the map. Why?

Abstract (arXiv)

This paper introduces a new framework for open-domain question answering in which the retriever and the reader iteratively interact with each other. The framework is agnostic to the architecture of the machine reading model, only requiring access to the token-level hidden representations of the reader. The retriever uses fast nearest neighbor search to scale to corpora containing millions of paragraphs. A gated recurrent unit updates the query at each step conditioned on the state of the reader and the reformulated query is used to re-rank the paragraphs by the retriever. We conduct analysis and show that iterative interaction helps in retrieving informative paragraphs from the corpus. Finally, we show that our multi-step-reasoning framework brings consistent improvement when applied to two widely used reader architectures DrQA and BiDAF on various large open-domain datasets --- TriviaQA-unfiltered, QuasarT, SearchQA, and SQuAD-Open.

Key facts. Cited by 48 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 8; 2023: 6; 2024: 9; 2025: 4; 2026: 3.

48 papers.

Sort:

By area:

  1. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  2. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  3. 2024Language Models with Conformal Factuality Guaranteescited by 131
  4. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  5. 2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
  6. 2021Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answeringcited by 50
  7. 2024BERGEN: A Benchmarking Library for Retrieval-Augmented Generationcited by 31
  8. 2021Challenges in Generalization in Open Domain Question Answeringcited by 30
  9. 2021Adaptive Information Seeking for Open-Domain Question Answeringcited by 29
  10. 2021Rider: Reader-Guided Passage Reranking for Open-Domain Question Answeringcited by 28
  11. 2022Visconde: Multi-document QA with GPT-3 and Neural Rerankingcited by 23
  12. 2021Database Reasoning Over Textcited by 20
36 more
  1. 2021Boosting Search Engines with Interactive Agentscited by 19
  2. 2021Rethinking Search: Making Domain Experts out of Dilettantescited by 18
  3. 2021Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphscited by 18
  4. 2022Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Surveycited by 14
  5. 2022From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answeringcited by 12
  6. 2022Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?cited by 10
  7. 2023LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoorscited by 9
  8. 2023Drilling Down into the Discourse Structure with LLMs for Long Document Question Answeringcited by 8
  9. 2021A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answeringcited by 7
  10. 2021Design Challenges for a Multi-Perspective Search Enginecited by 7
  11. 2022Interactive Question Answering Systems: Literature Reviewcited by 7
  12. 2022Understanding and Improving Zero-shot Multi-hop Reasoning in Generative Question Answeringcited by 7
  13. 2023Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generationcited by 7
  14. 20231-PAGER: One Pass Answer Generation and Evidence Retrievalcited by 7
  15. 2024CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph Reasoningcited by 7
  16. 2026ARC: Active and Reflection-driven Context Management for Long-Horizon Information Seeking Agentscited by 7
  17. 2024ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusioncited by 5
  18. 2021Memory Augmented Sequential Paragraph Retrieval for Multi-hop Question Answeringcited by 4
  19. 2021Weakly-Supervised Open-Retrieval Conversational Question Answeringcited by 4
  20. 2024Tree of Reviews: A Tree-based Dynamic Iterative Retrieval Framework for Multi-hop Question Answeringcited by 4
  21. 2025LLM-Specific Utility for Retrieval-Augmented Generationcited by 4
  22. 2021Simple and Efficient ways to Improve REALMcited by 3
  23. 2023Divide & Conquer for Entailment-aware Multi-hop Evidence Retrievalcited by 3
  24. 2021Generative Context Pair Selection for Multi-hop Question Answeringcited by 2
  25. 2022PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GANcited by 2
  26. 2023Strong and Efficient Baselines for Open Domain Conversational Question Answeringcited by 2
  27. 2024Location Aware Modular Biencoder for Tourism Question Answeringcited by 2
  28. 2024Passage-specific Prompt Tuning for Passage Reranking in Question Answering with Large Language Modelscited by 2
  29. 2025Prompting is not Enough: Exploring Knowledge Integration and Controllable Generationcited by 2
  30. 2024LightPAL: Lightweight Passage Retrieval for Open Domain Multi-Document Summarizationcited by 1
  31. 2025Bactrainus: Optimizing Large Language Models for Multi-hop Complex Question Answering Taskscited by 1
  32. 2021Building a Question Answering System for the Manufacturing Domaincited by 0
  33. 2024PrefRAG: Preference-Driven Multi-Source Retrieval Augmented Generationcited by 0
  34. 2025A Stepwise-Enhanced Reasoning Framework for Large Language Models Based on External Subgraph Generationcited by 0
  35. 2026SGR: A Stepwise Reasoning Framework for LLMs with External Subgraph Generationcited by 0
  36. 2026Stepwise Reasoning Enhancement for LLMs via External Subgraph Generationcited by 0