mlsanityData to 7 Oct 2026

Entity Retrieval for Answering Entity-Centric Questions

arXiv 2408.02795 ↗First posted 5 Aug 2024cs.IR cs.CLcited by 10

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

The similarity between the question and indexed documents is a crucial factor in document retrieval for retrieval-augmented question answering. Although this is typically the only method for obtaining the relevant documents, it is not the sole approach when dealing with entity-centric questions. In this study, we propose Entity Retrieval, a novel retrieval method which rather than relying on question-document similarity, depends on the salient entities within the question to identify the retrieval documents. We conduct an in-depth analysis of the performance of both dense and sparse retrieval methods in comparison to Entity Retrieval. Our findings reveal that our method not only leads to more accurate answers to entity-centric questions but also operates more efficiently.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 41 of its 60 references that are in the map. First posted on arXiv 5 Aug 2024.

Builds on

41 of 60 references.

References · 41

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  7. 2017Billion-scale similarity search with GPUscited by 2,477
  8. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  9. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  10. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  11. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  12. 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
29 more
  1. 2021Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategiescited by 736
  2. 2020How Much Knowledge Can You Pack Into the Parameters of a Language Model?cited by 713
  3. 2023In-Context Retrieval-Augmented Language Modelscited by 694
  4. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 691
  5. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  6. 2021Large Dual Encoders Are Generalizable Retrieverscited by 454
  7. 2018QuAC : Question Answering in Contextcited by 379
  8. 2023Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedbackcited by 351
  9. 2024The Power of Noise: Redefining Retrieval for RAG Systemscited by 275
  10. 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
  11. 2023LLM in a flash: Efficient Large Language Model Inference with Limited Memorycited by 170
  12. 2018Open Domain Question Answering Using Early Fusion of Knowledge Bases and Textcited by 167
  13. 2019Learning to Retrieve Reasoning Paths over Wikipedia Graph for Question Answeringcited by 147
  14. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  15. 2021End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answeringcited by 133
  16. 2023Improving Language Models via Plug-and-Play Retrieval Feedbackcited by 87
  17. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 59
  18. 2021Efficient Passage Retrieval with Hashing for Open-domain Question Answeringcited by 53
  19. 2020RepBERT: Contextualized Text Embeddings for First-Stage Retrievalcited by 46
  20. 2019KBQA: Learning Question Answering over QA Corpora and Knowledge Basescited by 44
  21. 2020Differentiable Reasoning over a Virtual Knowledge Basecited by 39
  22. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  23. 2017Strong Baselines for Simple Question Answering over Knowledge Graphs with and without Neural Networkscited by 12
  24. 2020Pretrained Transformers for Simple Question Answering over Knowledge Graphscited by 12
  25. 2023Large Language Models Meet Knowledge Graphs to Answer Factoid Questionscited by 11
  26. 2023SpEL: Structured Prediction for Entity Linkingcited by 11
  27. 2020Learning To Retrieve: How to Train a Dense Retrieval Model Effectively and Efficientlycited by 10
  28. 2024Unified Examination of Entity Linking in Absence of Candidate Setscited by 3
  29. 2019Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Setcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 4.

10 papers.

  1. 2025Scientific Paper Retrieval with LLM-Guided Semantic-Based Rankingcited by 10
  2. 2025SQUiD: Synthesizing Relational Databases from Unstructured Textcited by 4
  3. 2025FRASE: Structured Representations for Generalizable SPARQL Query Generationcited by 2
  4. 2025An Entity Linking Agent for Question Answeringcited by 2
  5. 2025NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddingscited by 2
  6. 2025Enhancing Frame Detection with Retrieval Augmented Generationcited by 1
  7. 2026RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answeringcited by 0
  8. 2026KGiRAG: An Iterative GraphRAG Approach for Responding Sensemaking Queriescited by 0
  9. 2026DeSQ: Decomposition-based SPARQL Query Generationcited by 0
  10. 2026Does the Selected Object Reach the Reader? Auditing Identity Handoffs in Grounded Language-Model Pipelinescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026EnSI-RAG: Entity-Structure-Indexed Retrieval-Augmented Generation for Long-Document Question Answering
  2. 2026EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development
  3. 2025Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities
  4. 2024REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering
  5. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation
  6. 2025SRAG: Structured Retrieval-Augmented Generation for Multi-Entity Question Answering over Wikipedia Graph
  7. 2025MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answering
  8. 2024DR-RAG: Applying Dynamic Document Relevance to Retrieval-Augmented Generation for Question-Answering