mlsanityData to 7 Oct 2026

A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques

arXiv 2106.14807 ↗First posted 28 Jun 2021cs.IR cs.CLcited by 69

Not on the map. Why?

Abstract (arXiv)

Recent developments in representational learning for information retrieval can be organized in a conceptual framework that establishes two pairs of contrasts: sparse vs. dense representations and unsupervised vs. learned representations. Sparse learned representations can further be decomposed into expansion and term weighting components. This framework allows us to understand the relationship between recently proposed techniques such as DPR, ANCE, DeepCT, DeepImpact, and COIL, and furthermore, gaps revealed by our analysis point to "low hanging fruit" in terms of techniques that have yet to be explored. We present a novel technique dubbed "uniCOIL", a simple extension of COIL that achieves to our knowledge the current state-of-the-art in sparse retrieval on the popular MS MARCO passage ranking dataset. Our implementation using the Anserini IR toolkit is built on the Lucene search library and thus fully compatible with standard inverted indexes.

Key facts. Cited by 69 papers in the map (data through 7 Oct 2026). Builds on 14 of its 25 references that are in the map. First posted on arXiv 28 Jun 2021.

Builds on

14 of 25 references.

References · 14

  1. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  2. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
  3. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  4. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 846
  5. 2020RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answeringcited by 410
  6. 2020Pretrained Transformers for Text Ranking: BERT and Beyondcited by 266
  7. 2021Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Samplingcited by 238
  8. 2020Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillationcited by 143
  9. 2021COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted Listcited by 113
  10. 2021Learning Passage Impacts for Inverted Indexescited by 68
  11. 2019Context-Aware Sentence/Passage Term Importance Estimation For First Stage Retrievalcited by 65
  12. 2021Efficient Passage Retrieval with Hashing for Open-domain Question Answeringcited by 53
2 more
  1. 2021A Replication Study of Dense Passage Retrievercited by 37
  2. 2020Complementing Lexical Retrieval with Semantic Residual Embeddingcited by 27

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 16; 2023: 13; 2024: 12; 2025: 15; 2026: 9.

69 papers.

Sort:

By area:

  1. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  2. 2021ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interactioncited by 464
  3. 2023Query2doc: Query Expansion with Large Language Modelscited by 146
  4. 2022Autoregressive Search Engines: Generating Substrings as Document Identifierscited by 112
  5. 2022From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effectivecited by 98
  6. 2024From Matching to Generation: A Survey on Generative Information Retrievalcited by 89
  7. 2021Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?cited by 59
  8. 2022Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generationcited by 47
  9. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  10. 2025A Survey of Multimodal Retrieval-Augmented Generationcited by 37
  11. 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 34
  12. 2021A Proposed Conceptual Framework for a Representational Approach to Information Retrievalcited by 24
38 more
  1. 2022Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reductioncited by 21
  2. 2022In Defense of Cross-Encoders for Zero-Shot Retrievalcited by 21
  3. 2022UnifieR: A Unified Retriever for Large-Scale Retrievalcited by 19
  4. 2022CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrievalcited by 19
  5. 2024Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decodingcited by 19
  6. 2022LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrievalcited by 15
  7. 2023Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboardcited by 15
  8. 2024Multimodal Learned Sparse Retrieval with Probabilistic Expansion Controlcited by 12
  9. 2024RGD: Multi-LLM Based Agent Debugger via Refinement and Generation Guidancecited by 12
  10. 2023Augmenting Black-box LLMs with Medical Textbooks for Biomedical Question Answeringcited by 11
  11. 2025Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connectorcited by 9
  12. 2024Mistral-SPLADE: LLMs for better Learned Sparse Retrievalcited by 8
  13. 2025Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrievalcited by 8
  14. 2025A Survey on Retrieval And Structuring Augmented Generation with Large Language Modelscited by 8
  15. 2023ESPN: Memory-Efficient Multi-Vector Information Retrievalcited by 7
  16. 2024ColBERT-XM: A Modular Multi-Vector Representation Model for Zero-Shot Multilingual Information Retrievalcited by 7
  17. 2023Exploring the Practicality of Generative Retrieval on Dynamic Corporacited by 6
  18. 2025Enhancing Lexicon-Based Text Embeddings with Large Language Modelscited by 6
  19. 2025Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansioncited by 6
  20. 2021Sparsifying Sparse Representations for Passage Retrieval by Top-k Maskingcited by 5
  21. 2022Query Expansion Using Contextual Clue Sampling with Language Modelscited by 5
  22. 2023CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrievalcited by 5
  23. 2022Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrievalcited by 4
  24. 2022Adam: Dense Retrieval Distillation with Adaptive Dark Examplescited by 4
  25. 2023Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrievalcited by 4
  26. 2024Measuring Bias in a Ranked List using Term-based Representationscited by 4
  27. 2025Balancing the Blend: An Experimental Analysis of Trade-offs in Hybrid Searchcited by 4
  28. 2023An Experimental Study on Pretraining Transformers from Scratch for IRcited by 3
  29. 2023Adapting Learned Sparse Retrieval for Long Documentscited by 3
  30. 2024Measuring Retrieval Complexity in Question Answering Systemscited by 3
  31. 2025An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doccited by 3
  32. 2025Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrievalcited by 3
  33. 2025Privacy-Preserving Reasoning with Knowledge-Distilled Parametric Retrieval Augmented Generationcited by 3
  34. 2022Hybrid Inverted Index Is a Robust Accelerator for Dense Retrievalcited by 2
  35. 2023NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoderscited by 2
  36. 2023SPRINT: A Unified Toolkit for Evaluating and Demystifying Zero-shot Neural Sparse Retrievalcited by 2
  37. 2026Visual Words Meet BM25: Sparse Auto-Encoder Visual Word Scoring for Image Retrievalcited by 2
  38. 2026AgentIR: A Workload-Adaptive Cascade Retrieval Substrate for Long-Term Conversational Memorycited by 2

50 most cited of 69 All 69 (JSON)