Information Retrieval

Also known as IR

Information retrieval develops methods for finding useful documents, passages, products, tables, code, and multimedia in response to a user's query. Systems range from lexical methods such as BM25 and learned sparse retrieval to dense embeddings, late-interaction models, hybrid ranking, and graph-based or agentic search. These methods support applications including web search, recommendation, and retrieval-augmented generation, where retrieved evidence must be both relevant and sufficient for the task. A central challenge is balancing accuracy with speed and cost: semantic similarity can miss structured, compositional, or domain-specific evidence, and strong retrieval scores do not always lead to useful answers.

Latest papers

476 papers61 papers in the last four weeks, up 36% on the four weeks before. 0.4% of all new papers.

AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce
Apr 22, 2026Biao Zhang, Lixin Chen, Bin Zhang +3Multimodal Large Language Models Cross-Modal Retrieval
Taobao & Tmall Group of Alibaba
Diagnosable ColBERT: Debugging Late-Interaction Retrieval Models Using a Learned Latent Space as Reference
Apr 21, 2026François RemyInterpretable ML Multi-Vector Retrieval
Parallia AI
Finding New Connections between Concepts from Medline Database Incorporating Domain Knowledge
Apr 21, 2026Yang Weikang, Chowdhury S. M. Mazharul Hoque, Jin WeiInformation Retrieval
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
Apr 20, 2026Shaden Alshammari, Kevin Wen, Abrar Zainal +5Mathematical Reasoning Benchmarks Multilingual Language Model Evaluation
MIT · HUMAIN · Individual Researcher +1
Document-as-Image Representations Fall Short for Scientific Retrieval
Apr 20, 2026Ghazal Khalighinejad, Raghuveer Thirukovalluru, Alexander H. Oh +1Multimodal IR Information Retrieval
Department of Computer Science, Duke University
Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps
Apr 20, 2026Zhichao Geng, Yang YangLearned Sparse Retrieval Information Retrieval
Amazon Web Service · Shanghai, China
Semantic Entanglement in Vector-Based Retrieval: A Formal Framework and Context-Conditioned Disentanglement Pipeline for Agentic RAG Systems
Apr 20, 2026Nick LoghmaniDocument Chunking Text Embeddings
Salesforce · School of Information Studies, Syracuse University
Matlas: A Semantic Search Engine for Mathematics
Apr 19, 2026Haocheng Ju, Leheng Chen, Peihao Wu +2Semantic Search Information Retrieval
School of Mathematical Sciences, Peking University, Beijing 100871, China · 3IQuest Research · 2Beijing International Center for Mathematical Research, Peking University, Beijing 100871, China +4
Bidirectional Small-Granularity Search between Code and Text
Apr 19, 2026Marco A. Valenzuela-Escárcega, Enrique Noriega-Atala, Gus Hahn-Powell +2AI-Assisted Scientific Research Cross-Modal Retrieval
Lex Machina · The University of Arizona, Tucson, AZ, USA
UsefulBench: Towards Decision-Useful Information as a Target for Information Retrieval
Apr 17, 2026Tobias Schimanski, Stefanie Lewandowski, Christian Woerle +3Information Retrieval IR Evaluation
University of Zurich · ETH Zurich · score4more GmbH +2
BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels
Apr 17, 2026Mengfei Lan, Lecheng Zheng, Halil KilicogluContrastive Learning Hierarchical Representation Learning
University of Illinois Urbana-Champaign
Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
Apr 16, 2026Yiqun Sun, Pengfei Wei, Lawrence B. HsiehRetrieval-Augmented Generation LLM Agent Skill Learning
Magellan Technology Research Institute (MTRI)
SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs
Apr 15, 2026Haoran Lou, Ziyan Liu, Chunxiao Fan +6Multimodal IR Cross-Modal Retrieval
School of Electronic Engineering, Beijing University of Posts and Telecommunications, China · Xiaohongshu Inc., China
From Relevance to Authority: Authority-aware Generative Retrieval in Web Search Engines
Apr 15, 2026Sunkyung Lee, Jihye Back, Donghyeon Jeon +4Information Retrieval Generative Retrieval
Sungkyunkwan University, Republic of Korea · Naver Corporation, Republic of Korea
NaviRAG: Towards Active Knowledge Navigation for Retrieval-Augmented Generation
Apr 14, 2026Jihao Dai, Dingjun Wu, Yuxuan Chen +4Retrieval-Augmented Generation Agentic RAG
Tsinghua University · Nanjing University · Northeastern University
Adaptive Query Routing: A Tier-Based Framework for Hybrid Retrieval Across Financial, Legal, and Medical Documents
Apr 14, 2026Afshan HashmiAdaptive RAG Information Retrieval
TRDC, Tuwaiq Academy, Riyadh, Saudi Arabia
The Effect of Document Selection on Query-focused Text Analysis
Apr 13, 2026Sandesh S Rangreji, Mian Zhong, Anjalie FieldData Selection Hybrid Retrieval
Johns Hopkins University
Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval
Apr 13, 2026Hao Xu, Rite Bo, Fausto Giunchiglia +2In-Context Learning Language Model Robustness
College of Computer Science and Technology, Jilin University, China · Department of Information Engineering and Computer Science, University of Trento, Italy
HeceTokenizer: A Syllable-Based Tokenization Approach for Turkish Retrieval
Apr 12, 2026Senol GulgonulTokenization Information Retrieval
Electrical and Electronics Engineering, Ostim Technical University, Ankara Turkey
NSFL: A Post-Training Neuro-Symbolic Fuzzy Logic Framework for Boolean Operators in Neural Embeddings
Apr 12, 2026Vladi Vexler, Ofer Idan, Gil Lederman +1Information Retrieval Neuro-Symbolic Reasoning
Huawei Tel-Aviv Research Center
FashionMV: Product-Level Composed Image Retrieval with Multi-View Fashion Data
Apr 11, 2026Peng Yuan, Bingyin Mei, Hui ZhangComposed Image Retrieval Information Retrieval
Tsinghua University Beijing, China
Regime-Conditional Retrieval: Theory and a Transferable Router for Two-Hop QA
Apr 10, 2026Andre BacellarMulti-Hop Retrieval Multi-Hop QA
Beyond Relevance: Utility-Centric Retrieval in the LLM Era
Apr 10, 2026Hengran Zhang, Minghao Tang, Keping Bi +1Information Retrieval RAG Evaluation
State Key Laboratory of AI Safety, ICT, CAS University of Chinese Academy of Sciences Beijing, China
SatIR: Scalable High-Recall Constraint-Satisfaction-Based Information Retrieval for Clinical Trials Matching
Apr 10, 2026Zikai Zhou, Yufei Jin, Yilin Xu +3Healthcare Satisfiability Modulo Theories
Department of Computer Science, Stanford University, Stanford, CA, USA · Samueli Electrical and Computer Engineering, UCLA, Los Angeles, CA, USA · Department of Computer Science, Emory University, Atlanta, GA, USA +1
Show Me the Infographic I Imagine: Intent-Aware Infographic Retrieval for Authoring Support
Apr 9, 2026Jing Xu, Jiarui Hu, Zhihao Shuai +2Information Retrieval Visual Document Retrieval
The Hong Kong University of Science and Technology (Guangzhou) · Nanjing University
Don't Measure Once: Measuring Visibility in AI Search (GEO)
Apr 8, 2026Julius Schulte, Malte Bleeker, Philipp KaufmannGenerative Engine Optimization Information Retrieval
Global Center for Entrepreneurship and Innovation University of St. Gallen 9000 St.Gallen, Switzerland · Marketing und Customer Insight University of St. Gallen 9000 St.Gallen, Switzerland
Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework
Apr 7, 2026Komal Kumar, Aman Chadha, Salman Khan +2AI-Assisted Scientific Research Information Retrieval
Mohamed bin Zayed University of Artificial Intelligence · AWS Generative AI Innovation Center, Amazon Web Services
SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems
Apr 6, 2026Varun Pratap BhardwajAgent Memory Information Retrieval
Independent Researcher, Solution Architect India
Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval
Apr 4, 2026Jun Li, Xuhang Lou, Jinpeng Wang +4Cross-Modal Retrieval Information Retrieval
Harbin Institute of Technology, Shenzhen · Tsinghua Shenzhen International Graduate School, Tsinghua University · Peng Cheng Laboratory
Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts
Apr 3, 2026Jinsook Lee, Kirk Vanacore, Zhuqian Zhou +2LLM-Assisted Annotation Retrieval-Augmented ICL
Cornell University Ithaca, NY, 14850, USA

Apr 22, 2026J/K move · Enter open · S save

AFMRL: Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning in E-commerce

Biao Zhang, Lixin Chen, Bin Zhang, Zongwei Wang+2

Taobao & Tmall Group of Alibaba

Multimodal Large Language Models Cross-Modal Retrieval Information Retrieval Multimodal Contrastive Learning Multimodal Learning

Open paper AskPDF arXiv

Multimodal representation is crucial for E-commerce tasks such as identical product retrieval. Large representation models (e.g., VLM2Vec) demonstrate strong multimodal understanding capabilities, yet they struggle with fine-grained semantic comprehension, which is essential for distinguishing highly similar items. To address this, we propose Attribute-Enhanced Fine-Grained Multi-Modal Representation Learning (AFMRL), which defines product fine-grained understanding as an attribute generation task. It leverages the generative power of Multimodal Large Language Models (MLLMs) to extract key attributes from product images and text, and enhances representation learning through a two-stage training framework: 1) Attribute-Guided Contrastive Learning (AGCL), where the key attributes generated by the MLLM are used in the image-text contrastive learning training process to identify hard samples and filter out noisy false negatives. 2) Retrieval-aware Attribute Reinforcement (RAR), where the improved retrieval performance of the representation model post-attribute integration serves as a reward signal to enhance MLLM's attribute generation during multimodal fine-tuning. Extensive experiments on large-scale E-commerce datasets demonstrate that our method achieves state-of-the-art performance on multiple downstream retrieval tasks, validating the effectiveness of harnessing generative models to advance fine-grained representation learning.