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

160 papers15 papers in the last four weeks, up 7% on the four weeks before. 0.1% of all new papers.

  1. Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers

    Sep 11, 2026Anubhav Shrestha, Safal Shrestha, Minwu Kim +2Information RetrievalMixture-of-Experts Language Models

  2. Parameter-Efficient Retrievers for Polish and European Languages

    Sep 11, 2026Sławomir Dadas, Rafał Poświata, Małgorzata Grębowiec +1Multilingual IRInformation Retrieval

  3. OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?

    Sep 8, 2026Xiao Yu Cindy Zhang, Wyeth Wasserman, Jian ZhuInformation RetrievalBiomedical IR

  4. EigenLI: Spectral Approximations to Late Interaction

    Sep 7, 2026Archish S, Sabyasachi Basu, Ankit Garg +2Late Interaction RetrievalMulti-Vector Retrieval

  5. ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers

    Sep 5, 2026Effrosyni Sokli, Isaac Roberts, Alexander Schulz +2Concept Activation VectorsInterpretable ML

  6. Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings

    Sep 3, 2026Peichun Hua, Yunming XiaoSecure Multi-Party ComputationEmbedding Compression

  7. Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories

    Sep 1, 2026Nabira Rashid, Manolis KellisLLM RerankingInformation Retrieval

  8. Learning from What You Retrieve: Online RL Fine-Tuning for Semantic Retrieval

    Aug 31, 2026Shaowei Wei, Chong Huang, Songtao Fang +3Semantic SearchRL for IR

  9. E-SENS: Exclusion-Sensitive Penalization for Negative-Constraint Retrieval

    Aug 31, 2026Yerang Kim, Jiyoon Myung, Joohyung HanLearning to RankDense Retrieval

  10. Efficient GPU Retrieval for Semantic Search

    Aug 29, 2026Dhritiman Das, Chujie Zheng, Ronak Kaoshik +18Semantic SearchDense Retrieval

  11. Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

    Aug 26, 2026Peichun Hua, Danyang Chen, Junan Zhang +5Privacy-Preserving RAGInformation Retrieval

  12. Keeping the Index Open: The Recommendation-Side Cost of Shared Search and Recommendation

    Aug 25, 2026Theodore Rogers, Joe Standerfer, Dmitrii Timoshenko +3Recommender SystemsCold-Start Recommendation

  13. Retrieval Needs Multivectors: An Exponential Separation

    Aug 21, 2026Mihir Agarwal, Viraj Agrawal, Sabyasachi Basu +2Multi-Vector RetrievalDense Retrieval

  14. Natural Language Code Retrieval for 1C:Enterprise: An Open Benchmark and Efficient Bi-Encoder

    Aug 20, 2026Konstantin Chesnokov, Chingiz MingazovCode SearchDense Retrieval

  15. GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval

    Aug 19, 2026Ernest Beta, Odysseas S. Chlapanis, Dimitrios Galanis +1Legal IRQuery Reformulation

  16. DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval

    Aug 18, 2026Jingyuan Wang, Richong Zhang, Zhijie Nie +2Dense RetrievalQuery Expansion

  17. Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors

    Aug 16, 2026Chunran ZhangRetrieval-Augmented GenerationRAG Evaluation

  18. Where Does Retrieval Fail? Evaluating RAG Architectures for Agricultural Advisory

    Aug 14, 2026Khan Raiyan Ibne Reza, Sanjana Aktar Maria, Sumaiya Tabassum NimiInformation RetrievalRAG Evaluation

  19. Retrieval Grounding Latent Reasoning for Dense Retrieval

    Aug 14, 2026Gang Zhou, Xiongxi Yu, Hu Tian +5Dense RetrievalImplicit Reasoning in Language Models

  20. DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation

    Aug 11, 2026Zhuchenyang Liu, Ziyi Wang, Yao Zhang +1VLM DistillationVisual Document Retrieval

  21. Bridging the Question-Answer Gap in Retrieval-Augmented Generation: Hypothetical Prompt Embeddings

    Jul 31, 2026Domen Vake, Jernej Vičič, Aleksandar TošićRetrieval-Augmented GenerationDense Retrieval