mlsanityData to 7 Oct 2026

Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering

arXiv 2305.17080 ↗First posted 26 May 2023cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

We propose EAR, a query Expansion And Reranking approach for improving passage retrieval, with the application to open-domain question answering. EAR first applies a query expansion model to generate a diverse set of queries, and then uses a query reranker to select the ones that could lead to better retrieval results. Motivated by the observation that the best query expansion often is not picked by greedy decoding, EAR trains its reranker to predict the rank orders of the gold passages when issuing the expanded queries to a given retriever. By connecting better the query expansion model and retriever, EAR significantly enhances a traditional sparse retrieval method, BM25. Empirically, EAR improves top-5/20 accuracy by 3-8 and 5-10 points in in-domain and out-of-domain settings, respectively, when compared to a vanilla query expansion model, GAR, and a dense retrieval model, DPR.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 34 of its 54 references that are in the map. First posted on arXiv 26 May 2023.

Builds on

34 of 54 references.

References · 34

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  7. 2017Billion-scale similarity search with GPUscited by 2,477
  8. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  9. 2021Multitask Prompted Training Enables Zero-Shot Task Generalizationcited by 1,462
  10. 2021DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharingcited by 1,219
  11. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  12. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
22 more
  1. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
  2. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 691
  3. 2019Passage Re-ranking with BERTcited by 629
  4. 2020Sparse, Dense, and Attentional Representations for Text Retrievalcited by 213
  5. 2020Generation-Augmented Retrieval for Open-domain Question Answeringcited by 186
  6. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 164
  7. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  8. 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 131
  9. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 112
  10. 2020Question Rewriting for Conversational Question Answeringcited by 93
  11. 2020Few-Shot Generative Conversational Query Rewritingcited by 85
  12. 2020Pre-trained Summarization Distillationcited by 70
  13. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 59
  14. 2021Learning to Retrieve Passages without Supervisioncited by 46
  15. 2021Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedbackcited by 45
  16. 2017Task-Oriented Query Reformulation with Reinforcement Learningcited by 39
  17. 2021Rider: Reader-Guided Passage Reranking for Open-Domain Question Answeringcited by 28
  18. 2022DQ-BART: Efficient Sequence-to-Sequence Model via Joint Distillation and Quantizationcited by 23
  19. 2021FastSeq: Make Sequence Generation Fastercited by 13
  20. 2021Towards Robust Neural Retrieval Models with Synthetic Pre-Trainingcited by 9
  21. 2020Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewritingcited by 6
  22. 2022Query Expansion Using Contextual Clue Sampling with Language Modelscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 4; 2025: 7; 2026: 2.

15 papers.

Sort:

By area:

  1. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  2. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 85
  3. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  4. 2025BEST-Route: Adaptive LLM Routing with Test-Time Optimal Computecited by 63
  5. 2025RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliabilitycited by 14
  6. 2024MockLLM: A Multi-Agent Behavior Collaboration Framework for Online Job Seeking and Recruitingcited by 8
  7. 2026OBLIQ-Bench: Exposing Overlooked Bottlenecks in Modern Retrievers with Latent and Implicit Queriescited by 5
  8. 2025Metadata-Driven Retrieval-Augmented Generation for Financial Question Answeringcited by 4
  9. 2024Zero-Shot Dense Retrieval with Embeddings from Relevance Feedbackcited by 3
  10. 2023Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answeringcited by 2
  11. 2025AdaRewriter: Unleashing the Power of Prompting-based Conversational Query Reformulation via Test-Time Adaptationcited by 2
  12. 2025NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrievalcited by 2
3 more
  1. 2026Beyond Single-Shot: Multi-step Tool Retrieval via Query Planningcited by 2
  2. 2024A Survey of Query Optimization in Large Language Modelscited by 1
  3. 2025Beyond Prompting: An Efficient Embedding Framework for Open-Domain Question Answeringcited by 1