mlsanityData to 14 Oct 2026

Autoregressive Entity Retrieval

arXiv 2010.00904 ↗First posted 2 Oct 2020cs.CL cs.IR cs.LGcited by 334

Not on the map. Why?

Abstract (arXiv)

Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities (e.g., one per Wikipedia article). The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. Current approaches can be understood as classifiers among atomic labels, one for each entity. Their weight vectors are dense entity representations produced by encoding entity meta information such as their descriptions. This approach has several shortcomings: (i) context and entity affinity is mainly captured through a vector dot product, potentially missing fine-grained interactions; (ii) a large memory footprint is needed to store dense representations when considering large entity sets; (iii) an appropriately hard set of negative data has to be subsampled at training time. In this work, we propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion. This mitigates the aforementioned technical issues since: (i) the autoregressive formulation directly captures relations between context and entity name, effectively cross encoding both; (ii) the memory footprint is greatly reduced because the parameters of our encoder-decoder architecture scale with vocabulary size, not entity count; (iii) the softmax loss is computed without subsampling negative data. We experiment with more than 20 datasets on entity disambiguation, end-to-end entity linking and document retrieval tasks, achieving new state-of-the-art or very competitive results while using a tiny fraction of the memory footprint of competing systems. Finally, we demonstrate that new entities can be added by simply specifying their names. Code and pre-trained models at https://github.com/facebookresearch/GENRE.

Key facts. Cited by 334 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 33; 2022: 76; 2023: 73; 2024: 67; 2025: 44; 2026: 41.

334 papers.

Sort:

By area:

  1. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 952
  2. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  3. 2021Editing Factual Knowledge in Language Modelscited by 553
  4. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  5. 2022Large Language Models Struggle to Learn Long-Tail Knowledgecited by 458
  6. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  7. 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
  8. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  9. 2022Unified Structure Generation for Universal Information Extractioncited by 221
  10. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  11. 2021PAQ: 65 Million Probably-Asked Questions and What You Can Do With Themcited by 200
  12. 2023Recommender Systems with Generative Retrievalcited by 198
38 more
  1. 2023OpenAGI: When LLM Meets Domain Expertscited by 197
  2. 2023Grammar-Constrained Decoding for Structured NLP Tasks without Finetuningcited by 197
  3. 2022CM3: A Causal Masked Multimodal Model of the Internetcited by 142
  4. 2021Simple Entity-Centric Questions Challenge Dense Retrieverscited by 140
  5. 2021Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extractioncited by 129
  6. 2023Large Language Models as Zero-Shot Conversational Recommenderscited by 127
  7. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 122
  8. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 113
  9. 2023Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entitiescited by 113
  10. 2022Re2G: Retrieve, Rerank, Generatecited by 102
  11. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  12. 2022PEER: A Collaborative Language Modelcited by 86
  13. 2022BioBART: Pretraining and Evaluation of A Biomedical Generative Language Modelcited by 83
  14. 2022Sequence-to-Sequence Knowledge Graph Completion and Question Answeringcited by 75
  15. 2022ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linkingcited by 74
  16. 2022CREPE: Open-Domain Question Answering with False Presuppositionscited by 72
  17. 2023Large Language Models and Knowledge Graphs: Opportunities and Challengescited by 71
  18. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  19. 2024Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?cited by 56
  20. 2021ProoFVer: Natural Logic Theorem Proving for Fact Verificationcited by 53
  21. 2021GenIE: Generative Information Extractioncited by 53
  22. 2021Multilingual Autoregressive Entity Linkingcited by 50
  23. 2023MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Predictioncited by 50
  24. 2022Generative Knowledge Graph Construction: A Reviewcited by 49
  25. 2022Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generationcited by 48
  26. 2023How Does Generative Retrieval Scale to Millions of Passages?cited by 48
  27. 2024Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Modelscited by 48
  28. 2023Learning to Rank in Generative Retrievalcited by 46
  29. 2022From Discrimination to Generation: Knowledge Graph Completion with Generative Transformercited by 45
  30. 2021Multi-task Retrieval for Knowledge-Intensive Taskscited by 44
  31. 2022Autoregressive Structured Prediction with Language Modelscited by 43
  32. 2022Contrastive Learning Reduces Hallucination in Conversationscited by 40
  33. 2022GERE: Generative Evidence Retrieval for Fact Verificationcited by 38
  34. 2023UP5: Unbiased Foundation Model for Fairness-aware Recommendationcited by 38
  35. 2023GeoLM: Empowering Language Models for Geospatially Grounded Language Understandingcited by 37
  36. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  37. 2022CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Taskscited by 36
  38. 2022Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuningcited by 35

50 most cited of 334 All 334 (JSON)