Dense Retrieval

Follow this topic Ask about this topic

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

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

Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model
Oct 23, 2026Yalda Taheri, Mohammad Hassan Heydari, Armon RasooliText Embedding Models Information Retrieval
Faculty of Engineering, Azad University · Faculty of Computer Engineering, University of Isfahan · Department of Electrical Engineering, Iran University of Science and Technology
What the Query Remembers: Query Abstraction Governs Lexical and Dense Retrieval of Classical Arabic Poetry
Oct 22, 2026Omar Farouk Zouak, Selma Mani, Larbi Said Chikh +1Lexical Retrieval Dense Retrieval
National School of Artificial Intelligence
Chunk Recomputation under Real Document Revisions: Measuring Update Cost and Retrieval Quality of Fixed, Recursive, and Content-Defined Chunking
Oct 22, 2026Yuning Bian, Lele Xu, Yifan Yuan +2Document Chunking RAG Evaluation
School of Computer Science and Technology, Anhui University of Technology, Ma’anshan, China
The Fusion Tax: A Diagnostic Analysis of When Hybrid Retrieval Hurts
Oct 22, 2026Aaditya Chauhan, Arun AgarwalHybrid Retrieval Data Fusion
Independent Researcher, Bothell, WA 98012 USA · Independent Researcher, Issaquah, WA 98027 USA
Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text Retrieval
Oct 15, 2026Yingtao Luo, Kangyi Zhao, Shiyi Du +1Text Embedding Models Efficient Language Model Reasoning
Carnegie Mellon University · University of Pittsburgh
Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap
Oct 13, 2026Renbo Tu, Yang Liu, Shuying SunPopularity Bias in Recommender Systems Generative Retrieval
Shopify · University of Toronto
Graph-free Retrieval with Graph-Modified Embeddings
Oct 13, 2026Federica Santi, Vasilije Marković, Daniel Scott +1Evidence Retrieval Graph-Based Retrieval
Cognee Inc
RALI@iKAT 2026: Retrieval-aware User Profile Denoising via Personalized Conversational Dense Retrieval
Oct 13, 2026Yuchen Hui, Fengran Mo, Jia Ao Sun +3Information Retrieval Conversational Search
RALI, Université de Montréal Montréal, Québec, Canada
KhyontekAI at CheckThat! 2026: Multilingual Dense Retrieval and Cross-Encoder Reranking for Scientific Web Claims
Oct 11, 2026Bhargab Jyoti Bhuyan, Pritam DekaScientific Document Retrieval Multilingual IR
Computer Science and Engineering Department, School of Engineering, Tezpur University, Assam, India · KhyontekAI, Guwahati, Assam, India
Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora
Oct 7, 2026Andrey Kuehlkamp, Priscila Correa Saboia Moreira, Samuel RundInformation Retrieval Dense Retrieval
Center for Research Computing, University of Notre Dame Notre Dame, Indiana, USA
OTel: Open Telco AI Datasets, Benchmarks, and Models
Oct 6, 2026Farbod Tavakkoli, Gregory Diamos, Kenneth Church +14Language Model Post-Training LLM Reranking
AT&T Chief Data Office · RelationalAI · Northeastern University +6
Multimodal Dual-Encoder Retrieval for Automated ICD Coding
Oct 3, 2026Abhinav Bohra, Anuj BohraAutomated Medical Coding Multimodal Learning
Amazon Seattle, USA · Rutgers University New Jersey, USA
MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search
Oct 2, 2026Sean Culatana, Shang-En Huang, Kang LiEmbedding Compression Dense Retrieval
Atlassian Mountain View, CA · National Taiwan University Taipei, Taiwan · Atlassian Bellevue, WA
Learning Query Encoders Can Be Hard Even When Vector Retrieval Is Geometrically Easy
Oct 2, 2026Anders Wikum, Nina Mishra, Amin Saberi +1Dense Retrieval Text Embeddings
Stanford University · Amazon AWS · Tel Aviv University
Effective Dense Retrieval using Only In-Context Examples
Sep 29, 2026Nour Jedidi, Abdul Basit Ali, Hang Li +1LLM Prompting Text Embedding Models
University of Waterloo · The University of Queensland
Retrieval Sensitivity to Identity Signals in Queries
Sep 29, 2026Andrew Tang, Nicholas Deas, Kathleen McKeown +1Information Retrieval Dense Retrieval
Columbia University, Department of Computer Science
Quantization Enables Private Dense Retrieval against Malicious Service Providers
Sep 28, 2026Louis Tremblay Thibault, Sofiane Azogagh, Marc-Olivier Killijian +1RAG Security Dense Retrieval
École de technologie supérieure and Mila · Eurecom · Université du Québec à Montréal
When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections
Sep 26, 2026Maojun Sun, Yancheng Yuan, Jian Huang +1Dense Retrieval Low-Rank Approximation
The Hong Kong Polytechnic University
Retail Product Search: A Practical Approach at Target
Sep 25, 2026Darshan Sonagara, Qujiaheng Zhang, Ankit Singh +1E-Commerce Search Information Retrieval
Data Sciences, Target Corporation Sunnyvale, CA, USA
Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation
Sep 24, 2026Tobias Deußer, Abhishek Pillai, Aurelio F. Bariviera +5Retrieval-Augmented Generation Legal QA
University of Bonn, Bonn, Germany · Lamarr-Institute for Machine Learning and Artificial Intelligence, Bonn, Germany · Universitat Rovira i Virgili, Reus, Spain +1
REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement
Sep 16, 2026Yerim Oh, Gunhee KimSynthetic Data Augmentation Information Retrieval
Seoul National University
Parser, Chunking, and Embedding Interactions in Retrieval-Augmented Generation over Indian Government Regulatory Documents
Sep 15, 2026Shubham Kumar SinghRAG Evaluation IR Evaluation
Mixture-of-Experts Language Models Can Be Strong and Efficient Retrievers
Sep 11, 2026Anubhav Shrestha, Safal Shrestha, Minwu Kim +2Information Retrieval Mixture-of-Experts Language Models
New York University Abu Dhabi · New York University
Parameter-Efficient Retrievers for Polish and European Languages
Sep 11, 2026Sławomir Dadas, Rafał Poświata, Małgorzata Grębowiec +1Multilingual IR Information Retrieval
National Information Processing Institute al. Niepodległości 188b, 00-608 Warsaw, Poland
Reading a Legal Question Word by Word: Embedding Trajectories of 2,144 Vietnamese Legal Headlines
Sep 8, 2026Tran Minh QuanText Embeddings Word Embeddings
OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?
Sep 8, 2026Xiao Yu Cindy Zhang, Wyeth Wasserman, Jian ZhuInformation Retrieval Biomedical IR
Graduate Program in Bioinformatics, The University of British Columbia · Centre for Molecular Medicine and Therapeutics, BC Children’s Hospital Research Institute · Department of Medical Genetics, The University of British Columbia +1
EigenLI: Spectral Approximations to Late Interaction
Sep 7, 2026Archish S, Sabyasachi Basu, Ankit Garg +2Late Interaction Retrieval Multi-Vector Retrieval
Temple · Microsoft Research India
Matryoshka Hash Representations for Model-Aware Compact Semantic Retrieval
Sep 7, 2026Peichun Hua, Yunming XiaoMatryoshka Representation Learning Embedding Compression
The Chinese University of Hong Kong, Shenzhen
ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers
Sep 5, 2026Effrosyni Sokli, Isaac Roberts, Alexander Schulz +2Interpretable ML Neural Network Interpretability
Department of Informatics, Systems and Communication, DISCo University of Milano-Bicocca Milan, Italy · CITEC - Center for Cognitive Interaction Technology Bielefeld University Bielefeld, Germany
Comparing Retrieval Methods for Academic Advisor Discovery: A Six-Method Study of 768 CS Faculty Profiles Across 9 US Universities
Sep 3, 2026Biraj SubediLearning to Rank Hybrid Retrieval
Independent Researcher

Oct 23, 2026J/K move · Enter open · S save

Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model

Yalda Taheri, Mohammad Hassan Heydari, Armon Rasooli

Faculty of Engineering, Azad University · Faculty of Computer Engineering, University of Isfahan · Department of Electrical Engineering, Iran University of Science and Technology

Text Embedding Models Information Retrieval Dense Retrieval Contrastive Learning Knowledge Distillation

Open paper AskPDF arXiv

Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training resources and compact embedding models. We present Yalda Embedding, a 595.8-million-parameter Persian retrieval model adapted from Qwen3-Embedding-0.6B using more than one million query-document pairs. On eight Persian retrieval tasks from FaMTEB, the model achieves the highest macro-average among the evaluated 0.6B models, scoring 0.5488 and outperforming Qwen3-Embedding-0.6B and F2LLM-v2-0.6B on every task. It also approaches Qwen3-Embedding-4B, winning on four tasks, tying on one, and trailing by 0.0075 in macro-average. An incremental ablation study examines contrastive batch size, optimization stabilization, and relational knowledge distillation from F2LLM-v2-8B. Under the one-epoch training setup, contrastive fine-tuning alone yields a modest mean improvement over initialization and regressions on two tasks. The final distilled configuration improves all eight tasks over the non-distilled model, raising the mean from 0.4813 to 0.5488 without increasing inference-time model size. These gains include hard-negative evaluation tasks despite training without explicitly mined or supplied hard negatives. We release model weights, training and evaluation code, the pairwise dataset, and its teacher-embedded counterpart, enabling inspection of data composition and training procedures, independent evaluation, and reuse without repeating expensive teacher inference.