mlsanityData to 14 Oct 2026

Retrieval-Enhanced Machine Learning

arXiv 2205.01230 ↗First posted 2 May 2022cs.LG cs.CL cs.IRcited by 47

Not on the map. Why?

Cited by 20 in Retrieval-augmented generation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Although information access systems have long supported people in accomplishing a wide range of tasks, we propose broadening the scope of users of information access systems to include task-driven machines, such as machine learning models. In this way, the core principles of indexing, representation, retrieval, and ranking can be applied and extended to substantially improve model generalization, scalability, robustness, and interpretability. We describe a generic retrieval-enhanced machine learning (REML) framework, which includes a number of existing models as special cases. REML challenges information retrieval conventions, presenting opportunities for novel advances in core areas, including optimization. The REML research agenda lays a foundation for a new style of information access research and paves a path towards advancing machine learning and artificial intelligence.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). Builds on 51 of its 80 references that are in the map. First posted on arXiv 2 May 2022.

Builds on

51 of 80 references.

References · 51

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  6. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  8. 2018Deep contextualized word representationscited by 2,290
  9. 2020Extracting Training Data from Large Language Modelscited by 2,189
  10. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  11. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  12. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
38 more
  1. 2022LaMDA: Language Models for Dialog Applicationscited by 1,220
  2. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
  3. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
  4. 2019Generalization through Memorization: Nearest Neighbor Language Modelscited by 800
  5. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  6. 2021Retrieval Augmentation Reduces Hallucination in Conversationcited by 692
  7. 2014Neural Turing Machinescited by 644
  8. 2021VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understandingcited by 602
  9. 2020Recipes for building an open-domain chatbotcited by 593
  10. 2019Video Object Segmentation using Space-Time Memory Networkscited by 438
  11. 2014Memory Networkscited by 363
  12. 2022Transformer Memory as a Differentiable Search Indexcited by 247
  13. 2018Long-Term Feature Banks for Detailed Video Understandingcited by 239
  14. 2021Internet-Augmented Dialogue Generationcited by 217
  15. 2020Nearest Neighbor Machine Translationcited by 209
  16. 2022MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognitioncited by 189
  17. 2021Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answeringcited by 178
  18. 2019Deeper Text Understanding for IR with Contextual Neural Language Modelingcited by 113
  19. 2020Entities as Experts: Sparse Memory Access with Entity Supervisioncited by 100
  20. 2018A Retrieve-and-Edit Framework for Predicting Structured Outputscited by 73
  21. 2020Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrievecited by 65
  22. 2021Baleen: Robust Multi-Hop Reasoning at Scale via Condensed Retrievalcited by 63
  23. 2017Neural Ranking Models with Weak Supervisioncited by 61
  24. 2017Few-Shot Learning Through an Information Retrieval Lenscited by 51
  25. 2020BERT-kNN: Adding a kNN Search Component to Pretrained Language Models for Better QAcited by 36
  26. 2021Controllable Semantic Parsing via Retrieval Augmentationcited by 35
  27. 2018A Memory Network Approach for Story-based Temporal Summarization of 360deg Videoscited by 29
  28. 2021RetrievalFuse: Neural 3D Scene Reconstruction with a Databasecited by 28
  29. 2021Passage Retrieval for Outside-Knowledge Visual Question Answeringcited by 25
  30. 2020Guided Transformer: Leveraging Multiple External Sources for Representation Learning in Conversational Searchcited by 23
  31. 2020Texture Memory-Augmented Deep Patch-Based Image Inpaintingcited by 22
  32. 2019Multi-step Entity-centric Information Retrieval for Multi-Hop Question Answeringcited by 20
  33. 2021Cross-Modal Retrieval Augmentation for Multi-Modal Classificationcited by 20
  34. 2019A Hybrid Retrieval-Generation Neural Conversation Modelcited by 18
  35. 2021More Robust Dense Retrieval with Contrastive Dual Learningcited by 15
  36. 2021Tip of the Tongue Known-Item Retrieval: A Case Study in Movie Identificationcited by 14
  37. 2017Relevance-based Word Embeddingcited by 12
  38. 2021Intra-Document Cascading: Learning to Select Passages for Neural Document Rankingcited by 10

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 10; 2024: 19; 2025: 4; 2026: 11.

47 papers.

Sort:

By area:

  1. 2024Optimization Methods for Personalizing Large Language Models through Retrieval Augmentationcited by 99
  2. 2024Evaluating Retrieval Quality in Retrieval-Augmented Generationcited by 90
  3. 2022FiD-Light: Efficient and Effective Retrieval-Augmented Text Generationcited by 63
  4. 2023Leveraging Large Language Models in Conversational Recommender Systemscited by 63
  5. 2023Information Retrieval Meets Large Language Models: A Strategic Report from Chinese IR Communitycited by 29
  6. 2024Stochastic RAG: End-to-End Retrieval-Augmented Generation through Expected Utility Maximizationcited by 29
  7. 2024Towards a Search Engine for Machines: Unified Ranking for Multiple Retrieval-Augmented Large Language Modelscited by 23
  8. 2023Adaptive Computation with Elastic Input Sequencecited by 22
  9. 2024Are Large Language Models Good at Utility Judgments?cited by 22
  10. 2024Comparing Retrieval-Augmentation and Parameter-Efficient Fine-Tuning for Privacy-Preserving Personalization of Large Language Modelscited by 21
  11. 2024Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decodingcited by 19
  12. 2022You can't pick your neighbors, or can you? When and how to rely on retrieval in the kNN-LMcited by 18
35 more
  1. 2023Improving Retrieval-Augmented Large Language Models via Data Importance Learningcited by 17
  2. 2024Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generationcited by 15
  3. 2023A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answeringcited by 14
  4. 2024Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximizationcited by 14
  5. 2024Accelerating Retrieval-Augmented Generationcited by 14
  6. 2024Cross-modal Retrieval for Knowledge-based Visual Question Answeringcited by 13
  7. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
  8. 2022Multi-Task Retrieval-Augmented Text Generation with Relevance Samplingcited by 10
  9. 2023KNN-LM Does Not Improve Open-ended Text Generationcited by 10
  10. 2026GrepSeek: Training Search Agents for Direct Corpus Interactioncited by 10
  11. 2023Query Understanding in the Age of Large Language Modelscited by 7
  12. 2023RRAML: Reinforced Retrieval Augmented Machine Learningcited by 6
  13. 2024Retrieval-Augmented Mining of Temporal Logic Specifications from Datacited by 5
  14. 2025LTRR: Learning To Rank Retrievers for LLMscited by 4
  15. 2025RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generationcited by 4
  16. 2023Multivariate Representation Learning for Information Retrievalcited by 3
  17. 2024Multi-Class Quantum Convolutional Neural Networkscited by 3
  18. 2024Retrieval-Augmented Feature Generation for Domain-Specific Classificationcited by 3
  19. 2025A Benchmark for Open-Domain Numerical Fact-Checking Enhanced by Claim Decompositioncited by 3
  20. 2026CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Searchcited by 3
  21. 2024Exploring ChatGPT for Next-generation Information Retrieval: Opportunities and Challengescited by 2
  22. 2023ROMO: Retrieval-enhanced Offline Model-based Optimizationcited by 1
  23. 2024Retrieval and Distill: A Temporal Data Shift-Free Paradigm for Online Recommendation Systemcited by 1
  24. 2024Generative Language Models with Retrieval Augmented Generation for Automated Short Answer Scoringcited by 1
  25. 2026Analytical Searchcited by 1
  26. 2026Training Dense Retrievers with Multiple Positive Passagescited by 1
  27. 2026Evaluation of Agents under Simulated AI Marketplace Dynamicscited by 1
  28. 2024LML-DAP: Language Model Learning a Dataset for Data-Augmented Predictioncited by 0
  29. 2025Plan-and-Refine: Diverse and Comprehensive Retrieval-Augmented Generationcited by 0
  30. 2026Retrieval-Enhanced Real Estate Appraisalcited by 0
  31. 2026Improving MPI Error Detection and Repair with Large Language Models and Bug Referencescited by 0
  32. 2026A Unified Model and Document Representation for On-Device Retrieval-Augmented Generationcited by 0
  33. 2026The Pre-Training Study of Expanded-SPLADE Models on Web Document Titlescited by 0
  34. 2026ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generationcited by 0
  35. 2026Fast and Accurate: Improving Personalized LLM Performance by Semantic Concentration Inspired Workload Split between RAG and Fine-Tuningcited by 0