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.

Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG
May 31, 2026Francielle Vargas, João Robiatti, Diego Alves +6Retrieval-Augmented Generation Evidence Selection
University of Chile · São Paulo State University · Saarland University +4
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
May 31, 2026Zhicheng Zhang, Jiwei Tang, Kuicai Dong +9Contrastive Learning Hard Negative Mining
Shenzhen International Graduate School, Tsinghua University Shenzhen, China · Huawei Technologies Co., Ltd. Shenzhen, China · City University of Hong Kong Hong Kong SAR, China +4
Test-Time Training for Zero-Resource Dense Retrieval Reranking
May 31, 2026Shiyan Liu, Yichen LiZero-Shot Learning Learning to Rank
Huazhong University of Science and Technology · ByteDance
Xetrieval: Explaining Dense Retrieval through Feature Elicitation
May 28, 2026Zhixin Cai, Jun Bai, Yang Liu +7Text Embedding Models Dense Retrieval
School of Computer Science and Engineering, Beihang University · State Key Laboratory of General Artificial Intelligence, BIGAI
Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies
May 28, 2026Benjamin Clavié, Sean Lee, Aamir Shakir +1Learned Sparse Retrieval Information Retrieval
Mixedbread AI · National Institute of Informatics (NII) · University of Tsukuba
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
May 28, 2026Vaishali Senthil, Ashutosh Hathidara, Sebastian SchreiberTool-Augmented Language Model Agents LLM Tool Use
SAP Labs
Spectral Retrieval: Multi-Scale Sinc Convolution over Token Embeddings for Localized Retrieval in LLM Multi-Agent Systems
May 23, 2026Andrea MorandiLate Interaction Retrieval Multi-Vector Retrieval
Cisco Systems, Inc.
HARNESS-LM: A Three-Phase Training Recipe for Harnessing SLMs in Sponsored Search Retrieval
May 22, 2026Vipul Gupta, Shikhar Mohan, Lakshya Kumar +4Online Advertising Small Language Models
Microsoft AI India
Is Dimensionality a Barrier for Retrieval Models?
May 22, 2026Kiril Bangachev, Guy Bresler, Jonathan Kogan +1Dense Retrieval
Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge, MA, 02139
A Comparative Study of Language Models for Khmer Retrieval-Augmented Question Answering
May 21, 2026Sereiwathna Ros, Phannet Pov, Ratanaktepi Chhor +3Retrieval-Augmented Generation Multilingual QA
Department of Computer Science, Chungbuk National University, Cheongju, South Korea · Department of Big Data, Chungbuk National University, Cheongju, South Korea · General Department of Information and Communication Technology, Ministry of Post and Telecommunications, Phnom Penh, Cambodia +2
DIVE: Embedding Compression via Self-Limiting Gradient Updates
May 20, 2026Dongfang ZhaoContrastive Learning Embedding Compression
High-Dimensional Concentration and Retrieval Instability in Embedding Spaces: Implications for Retrieval-Augmented Generation
May 19, 2026Ernesto Lopez FuneNeural Representation Geometry Retrieval Robustness
DE · Data Empirix, Paris, France
Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
May 14, 2026Sahil Sen, Akhil Kasturi, Elias Lumer +2Agentic Search LLM Agent Evaluation
PricewaterhouseCoopers, U.S.
ConRetroBert: EMA Stabilized Dual Encoders for Template-Based Single-Step Retrosynthesis
May 12, 2026Mohammad Jahid Ibna Basher, Ali Khodabandeh Yalabadi, Ivan Garibay +1Dense Retrieval Retrosynthesis
Department of Industrial Engineering University of Central Florida Orlando, FL 32816
Test-Time Compute for Frozen Embedding Models through Agentic Program Search
May 12, 2026Han XiaoInference-Time Optimization Text Embedding Models
Jina AI by Elastic
The Interference Gap: Comparing Retrieval Bounds in Human Memory and RAG Systems
May 9, 2026Dongxin Guo, Jikun Wu, Siu-Ming YiuComputational Cognitive Modeling Episodic Memory
The University of Hong Kong, Hong Kong, China · Stellaris AI Limited, Hong Kong, China · Brain Investing Limited, Hong Kong, China
DiffRetriever: Parallel Representative Tokens for Retrieval with Diffusion Language Models
May 8, 2026Shuai Wang, Yu Yin, Shengyao Zhuang +2Multi-Vector Retrieval Diffusion Language Models
The University of Queensland, Brisbane, QLD, Australia · CSIRO
MINER: Mining Multimodal Internal Representation for Efficient Retrieval
May 7, 2026Weien Li, Rui Song, Zeyu Li +8Multimodal Embedding Visual Document Retrieval
McGill University · MIT - Massachusetts Institute of Technology · University of Cambridge +3
SkillRet: A Large-Scale Benchmark for Skill Retrieval in LLM Agents
May 7, 2026Ryangkyung Kang, Hongcheol Cho, Youngeun KimAI Agent Benchmarks LLM Agent Skill Retrieval
ThakiCloud
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
May 5, 2026Yilun Zhao, Jinbiao Wei, Tingyu Song +3Agentic Search Synthetic Data Generation
Yale NLP Lab · National University of Singapore · NYU Shanghai
Reproducing Complex Set-Compositional Information Retrieval
May 5, 2026Vincent Degenhart, Dewi Timman, Arjen P. de Vries +2Query Complexity Lexical Retrieval
Radboud University · Nijmegen, NL
GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing
May 4, 2026Jinliang XuDense Retrieval
China Academy of Information and Communications Technology, Beijing, China
Retrieval with Multiple Query Vectors through Anomalous Pattern Detection
May 3, 2026Allassan Tchangmena A Nken, Baimam Boukar Jean Jacques, Miriam Rateike +2Multi-Vector Retrieval Dense Retrieval
1IBM · University of Galway · 3Carnegie Mellon University Africa +1
Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces
May 1, 2026Mohit Kumar, Somayeh Kargaran, Bernhard A. Moser +1Legal IR Kernel Methods
University of Rostock, Germany · Software Competence Center Hagenberg GmbH, Austria Hagenberg, Austria
Toward a Scientific Discovery Engine for Weather and Climate Data: A Visual Analytics Workbench for Embedding-Based Exploration
May 1, 2026Nihanth W. Cherukuru, Matt Rehme, Kirsten J. Mayer +4Scientific Visualization Data Visualization
NSF National Center for Atmospheric Research, Boulder, Colorado USA
Hypencoder Revisited: Reproducibility and Analysis of Non-Linear Scoring for First-Stage Retrieval
Apr 29, 2026Arne Eichholtz, Yongkang Li, Jutte Vijverberg +2Learning to Rank Hypernetworks
University of Amsterdam Amsterdam, The Netherlands
Improving Robustness of Tabular Retrieval via Representational Stability
Apr 27, 2026Kushal Raj Bhandari, Adarsh Singh, Jianxi Gao +2Retrieval Robustness Information Retrieval
Department of Computer Science Arizona State University Tempe, Arizona, USA · ScaleAI San Francisco, CA, USA
Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA
Apr 25, 2026Teng Chen, Sheng Xu, Feixiang Guo +4Language Model Distillation Information Retrieval
Geely AI Lab Ningbo, Zhejiang, China
Aligning Dense Retrievers with LLM Utility via Distillation
Apr 24, 2026Rajinder Sandhu, Di Mu, Cheng Chang +4Retrieval-Augmented Generation Dense Retrieval
Layer 6 AI · Toronto, ON, Canada · Dalhousie University +1
Citation-Driven Multi-View Training for Patent Embeddings: QaECTER and Sophia-Bench
Apr 24, 2026Younes Djemmal, You Zuo, Kim Gerdes +1Legal IR Text Embedding Models
ALMAnaCH · 1AI Lab, Questel, Paris, France · 3Inria, Paris, France +3

May 31, 2026J/K move · Enter open · S save

Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG

Francielle Vargas, João Robiatti, Diego Alves, Lucas Pascotti Valem+5

University of Chile · São Paulo State University · Saarland University+4

Retrieval-Augmented Generation Evidence Selection Evidence Retrieval Dense Retrieval

Open paper AskPDF arXiv

Ensuring factuality and interpretability in RAG remains an open and urgent problem. We introduce Contrastive Evidence Rationale Attention (CERA), the first retrieval framework to employ subjectivity-based hard negative selection and inject an evidential inductive bias into contrastive learning through an auxiliary attention alignment loss. CERA fine-tunes a dense retriever using two training objectives: triplet-based contrastive learning and interpretable attention alignment, which supervises CLS-to-token attention using a part-of-speech-weighted masking distribution over human-annotated factual rationales as evidence signals. Experiments on a large corpus of clinical trial reports demonstrate that the subjectivity-based hard negative selection substantially improves retrieval effectiveness compared to both Contriever and hard negative selection baselines. Furthermore, rationale alignment improves faithfulness while maintaining competitive retrieval performance, supporting the hypothesis that attention can serve as a more faithful explanation of model behavior when guided by human rationales. Moving beyond topical similarity, CERA enables the retriever to identify the specific tokens that constitute supporting evidence, promoting more interpretable evidence selection in RAG systems.