Dense Retrieval

Ask about this topic

Overview

Dense retrieval encodes queries and candidates as vectors, then uses nearest-neighbor search to find relevant results, often where exact keyword matching is inadequate. Common approaches include dual encoders trained with contrastive learning and hard negatives, late-interaction models that match token-level representations, and hybrid systems that combine dense scores with lexical retrieval or reranking. Researchers evaluate these methods on benchmarks such as BEIR and domain-specific tests, while also developing compact indexes, multilingual and specialized retrievers, and retrieval for long documents or agent tasks. A central tension is that stronger models and richer representations can improve difficult or compositional search but cost more to train and serve; generalization, robustness, fairness, and reliable constraint handling remain open challenges.

Latest papers

CardsList

152 papers17 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. BACH: A Bayesian Admixture of Contrastive Heads for Multi-Interest Two-Tower Retrieval

    Jul 9, 2026Quoc Phong Nguyen, Paul Albert, Long Vuong +2Bayesian Mixture ModelsMulti-Vector Retrieval

    Amazon

  2. Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls

    Jul 3, 2026Kirill Shevkunov, Andrey Ploskonosov, Liudmila ProkhorenkovaLearning to RankInformation Retrieval

    1Yandex.

  3. Real-Time Hard Negative Sampling via LLM-based Clustering for Large-Scale Two-Tower Retrieval

    Jul 1, 2026Ivan Ji, Liuyi Hu, Harrison +6Popularity BiasHard Negative Mining

    Zihao · 1Meta · Xiangjun

  4. SHARD: cell-keyed residual splitting for alignment-resistant private dense retrieval

    Jun 26, 2026Sergey KurilenkoData LeakageDense Retrieval

    Moscow Institute of Physics and Technology

  5. Hybrid privacy-aware semantic search: SVD-truncated document geometry and CKKS-encrypted query reranking under a restricted threat model

    Jun 24, 2026Sergey KurilenkoSemantic SearchHybrid Retrieval

    Moscow Institute of Physics and Technology, Dolgoprudny, Moscow Region, Russia.

  6. DREAM: Dense Retrieval Embeddings via Autoregressive Modeling

    Jun 23, 2026Yixuan Tang, Yi YangInformation RetrievalText Embedding Models

    The Hong Kong University of Science and Technology

  7. PETRA: Transforming Web Text for Petroleum-Engineering Domain Adaptation

    Jun 23, 2026Kirill Dubovikov, Omar El Mansouri, Hachem Madmoun +12Domain AdaptationSynthetic Data Generation

    Mohamed bin Zayed University of Artificial Intelligence · Inception AI

  8. Schema-First Retrieval: Embedding Catalogs for Natural Language Analytics

    Jun 23, 2026Adarsh Agrawal, Shashank IndukuriTable RetrievalText-to-SQL

  9. Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders

    Jun 19, 2026Wonseok Shin, Songkuk KimText EmbeddingsSentence Embeddings

    Yonsei University

  10. SHIFT: Semantic Harmonization via Index-side Feature Transformation for Multilingual Information Retrieval

    Jun 17, 2026Youngjoon Jang, Seongtae Hong, Hyeonseok Moon +1Cross-Lingual Representation AlignmentMultilingual IR

    Department of Computer Science and Engineering, Korea University

  11. Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation

    Jun 17, 2026Shanshan Lyu, Yiwei Wang, Yujun Cai +2Long-Context RetrievalDocument Chunking

    Chongqing University · State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences +2

  12. MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval

    Jun 16, 2026Amirhossein Abaskohi, Raymond Li, Gaetano Cimino +3Retrieval-Augmented GenerationInformation Retrieval

    University of British Columbia · University of Salerno · ServiceNow Research

  13. SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG

    Jun 16, 2026Amirhossein Abaskohi, Issam H. Laradji, Peter West +1Document ChunkingRetrieval-Augmented Generation

    University of British Columbia · ServiceNow Research

  14. Non-negative Elastic Net Decoding for Information Retrieval

    Jun 16, 2026Koki Okajima, Yasutoshi Ida, Tsukasa Yoshida +1Representation LearningInformation Retrieval

    NTT, Inc.

  15. Temporal Preference Optimization for Unsupervised Retrieval

    Jun 16, 2026HyunJin Kim, Jaejun Shim, Young Jin Kim +1Temporal IRPreference Optimization

    1Sungkyunkwan University, Suwon, South Korea · 2Microsoft, Redmond, USA

  16. Filtered ANN as a Phase Transition: When Selectivity-Estimation Error Causes Plan Regret

    Jun 15, 2026Madhulatha Mandarapu, Sandeep KunkunuruExact Nearest Neighbor SearchRegret Minimization

    VaidhyaMegha Private Limited, India

  17. ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion

    Jun 12, 2026Karamvir Singh, Arvind JainRetrieval-Augmented GenerationAdaptive Retrieval

    HighLevel, Inc.

  18. When Does Mixing Help? Analyzing Query Embedding Interpolation in Multilingual Dense Retrieval

    Jun 11, 2026Tongyao Zhu, Chao-Ming Huang, Min-Yen KanMultilingual IRDense Retrieval

    National University of Singapore

  19. What Limits Does Quantization Place on Dense Top-kk Retrieval? A Theoretical Study

    Jun 10, 2026Koki Okajima, Tsukasa YoshidaInformation RetrievalLow-Bit Quantization

    NTT, Inc.

  20. The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search

    Jun 9, 2026Charith Chandra Sai Balne, Rithwik Maramraju, Siddharth Pratap Singh +4Contrastive LearningInformation Retrieval

    Walmart Global Tech USA · Walmart Global Tech2026 USA

  21. When More Documents Hurt RAG: Measuring and Reducing Vector Search Dilution with Domain-Scoped Retrieval

    Jun 9, 2026Nabaraj Subedi, Ahmed Abdelaty, Shivanand Venkanna SheshappanavarRetrieval-Augmented GenerationAgentic RAG

    Dept. of Electrical Engineering & Computer Science University of Wyoming, Laramie, WY 82071, USA · Dept. of Civil, Architectural Engineering & Construction Management University of Wyoming, Laramie, WY 82071, USA

  22. ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval

    Jun 9, 2026Taiheng PanCross-Encoder RerankingConversational Memory

    School of Computing and Information Systems University of Melbourne

  23. NTILC: Neural Tool Invocation via Learned Compression

    Jun 4, 2026Andrew Krikorian, Yayuan Li, Jason J. CorsoLLM Inference AccelerationLLM Tool Use

    Department of Robotics University of Michigan Ann Arbor, MI 48104 · Department of ECE University of Michigan Ann Arbor, MI 48104

  24. ColBERTSaR: Sparsified ColBERT Index via Product Quantization

    Jun 4, 2026Eugene Yang, Andrew Yates, Dawn Lawrie +3Vector QuantizationMulti-Vector Retrieval

    Johns Hopkins University, Baltimore, MD, USA

  25. Training-Free Lexical-Dense Fusion for Conversational-Memory Retrieval

    Jun 2, 2026Christian LysenstøenLate Interaction RetrievalLexical Retrieval

    Inland Norway University of Applied Sciences · Visiting student, University of California, Berkeley

  26. The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents

    Jun 1, 2026Shwan Ashrafi, Dan RothFokker–Planck EquationAlgorithmic Fairness

    Oracle AI

  27. Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors

    Jun 1, 2026Francisco Valentini, Edgar Altszyler, Martin FajcikIR EvaluationDense Retrieval

    CONICET-Universidad de Buenos Aires. Instituto de Ciencias de la Computación (ICC). Buenos Aires, Argentina · Quantit, Buenos Aires, Argentina · Brno University of Technology, Brno, Czech Republic

  28. Attention Calibration for Position-Fair Dense Retrieval

    Jun 1, 2026Andrianos Michail, Elias Schuhmacher, Juri Opitz +2Information RetrievalAttention Mechanisms

    University of Zurich · Zurich, Switzerland

  29. RCEM: Robust Conversational Search EMbedder in Distributional Shift

    Jun 1, 2026Kilho Son, Paul Hsu, Cha Zhang +1Distribution ShiftConversational Search

    Microsoft Corporation

  30. Semantic Retrieval for Product Search in E-Commerce

    May 31, 2026Nikhil Kothari, Saksham Samdani, Ritam Mallick +3Learning to RankSemantic Search

    Flipkart, India