{"total":119,"rows":[{"id":"2212.10496","title":"Precise Zero-Shot Dense Retrieval without Relevance Labels","created":"2022-12-20","cited_by_count":517,"area":null},{"id":"2401.00368","title":"Improving Text Embeddings with Large Language Models","created":"2023-12-31","cited_by_count":303,"area":null},{"id":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235,"area":null},{"id":"2302.07452","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","created":"2023-02-15","cited_by_count":118,"area":null},{"id":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107,"area":null},{"id":"2312.06648","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","created":"2023-12-11","cited_by_count":88,"area":null},{"id":"2310.07554","title":"A Multi-Task Embedder For Retrieval Augmented LLMs","created":"2023-10-11","cited_by_count":64,"area":"rag"},{"id":"2202.05144","title":"InPars: Data Augmentation for Information Retrieval using Large Language Models","created":"2022-02-10","cited_by_count":62,"area":null},{"id":"2206.10128","title":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation","created":"2022-06-21","cited_by_count":48,"area":null},{"id":"2212.02027","title":"Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer","created":"2022-12-05","cited_by_count":45,"area":null},{"id":"2205.09153","title":"ERNIE-Search: Bridging Cross-Encoder with Dual-Encoder via Self On-the-fly Distillation for Dense Passage Retrieval","created":"2022-05-18","cited_by_count":41,"area":null},{"id":"2404.18443","title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers","created":"2024-04-29","cited_by_count":38,"area":null},{"id":"2303.00807","title":"UDAPDR: Unsupervised Domain Adaptation via LLM Prompting and Distillation of Rerankers","created":"2023-03-01","cited_by_count":37,"area":null},{"id":"2304.01982","title":"Rethinking the Role of Token Retrieval in Multi-Vector Retrieval","created":"2023-04-04","cited_by_count":31,"area":null},{"id":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2410.17952","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","created":"2024-10-23","cited_by_count":28,"area":"rag"},{"id":"2309.08541","title":"When do Generative Query and Document Expansions Fail? A Comprehensive Study Across Methods, Retrievers, and Datasets","created":"2023-09-15","cited_by_count":26,"area":null},{"id":"2305.04808","title":"CAT: A Contextualized Conceptualization and Instantiation Framework for Commonsense Reasoning","created":"2023-05-08","cited_by_count":25,"area":"lr"},{"id":"2311.05800","title":"Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval","created":"2023-11-10","cited_by_count":24,"area":null},{"id":"2204.12755","title":"A Thorough Examination on Zero-shot Dense Retrieval","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2212.06121","title":"In Defense of Cross-Encoders for Zero-Shot Retrieval","created":"2022-12-12","cited_by_count":21,"area":null},{"id":"2210.15212","title":"COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning","created":"2022-10-27","cited_by_count":20,"area":null},{"id":"2206.02873","title":"No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval","created":"2022-06-06","cited_by_count":17,"area":null},{"id":"2505.16967","title":"Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMs","created":"2025-05-22","cited_by_count":17,"area":null},{"id":"2203.10232","title":"DuReader_retrieval: A Large-scale Chinese Benchmark for Passage Retrieval from Web Search Engine","created":"2022-03-19","cited_by_count":15,"area":null},{"id":"2407.06992","title":"Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective","created":"2024-07-09","cited_by_count":15,"area":null},{"id":"2208.03197","title":"Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey","created":"2022-08-05","cited_by_count":14,"area":null},{"id":"2301.02998","title":"InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers","created":"2023-01-08","cited_by_count":14,"area":null},{"id":"2305.02564","title":"RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2409.02685","title":"RouterRetriever: Routing over a Mixture of Expert Embedding Models","created":"2024-09-04","cited_by_count":12,"area":"moe"},{"id":"2305.07402","title":"Synergistic Interplay between Search and Large Language Models for Information Retrieval","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2305.11052","title":"BERM: Training the Balanced and Extractable Representation for Matching to Improve Generalization Ability of Dense Retrieval","created":"2023-05-18","cited_by_count":11,"area":null},{"id":"2306.16478","title":"Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2212.09598","title":"Query-as-context Pre-training for Dense Passage Retrieval","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2305.13691","title":"Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering","created":"2023-05-23","cited_by_count":9,"area":"synth"},{"id":"2407.10691","title":"$\\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2307.02740","title":"Dense Retrieval Adaptation using Target Domain Description","created":"2023-07-06","cited_by_count":8,"area":null},{"id":"2403.19317","title":"Beyond Borders: Investigating Cross-Jurisdiction Transfer in Legal Case Summarization","created":"2024-03-28","cited_by_count":8,"area":null},{"id":"2210.01371","title":"A Study on the Efficiency and Generalization of Light Hybrid Retrievers","created":"2022-10-04","cited_by_count":7,"area":null},{"id":"2309.09403","title":"Selecting which Dense Retriever to use for Zero-Shot Search","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2410.03780","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","created":"2024-10-03","cited_by_count":7,"area":"rag"},{"id":"2502.11181","title":"Improving Scientific Document Retrieval with Concept Coverage-based Query Set Generation","created":"2025-02-16","cited_by_count":7,"area":null},{"id":"2210.12865","title":"Knowledge Transfer from Answer Ranking to Answer Generation","created":"2022-10-23","cited_by_count":6,"area":null},{"id":"2302.03754","title":"Augmenting Zero-Shot Dense Retrievers with Plug-in Mixture-of-Memories","created":"2023-02-07","cited_by_count":6,"area":null},{"id":"2303.11648","title":"Improving Content Retrievability in Search with Controllable Query Generation","created":"2023-03-21","cited_by_count":6,"area":null},{"id":"2303.13386","title":"Compositional Zero-Shot Domain Transfer with Text-to-Text Models","created":"2023-03-23","cited_by_count":6,"area":null},{"id":"2210.07988","title":"PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population","created":"2022-10-14","cited_by_count":5,"area":"lr"},{"id":"2210.13749","title":"AugCSE: Contrastive Sentence Embedding with Diverse Augmentations","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2304.01003","title":"QUADRo: Dataset and Models for QUestion-Answer Database Retrieval","created":"2023-03-30","cited_by_count":5,"area":null},{"id":"2306.16143","title":"Generative User-Experience Research for Developing Domain-specific Natural Language Processing Applications","created":"2023-06-28","cited_by_count":5,"area":null},{"id":"2308.10025","title":"I3: Intent-Introspective Retrieval Conditioned on Instructions","created":"2023-08-19","cited_by_count":5,"area":null},{"id":"2312.15784","title":"AHAM: Adapt, Help, Ask, Model -- Harvesting LLMs for literature mining","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2404.02489","title":"DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2502.17957","title":"On Synthetic Data Strategies for Domain-Specific Generative Retrieval","created":"2025-02-25","cited_by_count":5,"area":"synth"},{"id":"2508.01643","title":"ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddings","created":"2025-08-03","cited_by_count":5,"area":"rag"},{"id":"2205.11498","title":"Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval","created":"2022-05-23","cited_by_count":4,"area":null},{"id":"2208.04232","title":"Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval","created":"2022-08-08","cited_by_count":4,"area":null},{"id":"2208.05753","title":"Disentangled Modeling of Domain and Relevance for Adaptable Dense Retrieval","created":"2022-08-11","cited_by_count":4,"area":null},{"id":"2210.10695","title":"Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking","created":"2022-10-19","cited_by_count":4,"area":null},{"id":"2212.10764","title":"Learning List-Level Domain-Invariant Representations for Ranking","created":"2022-12-21","cited_by_count":4,"area":null},{"id":"2311.15564","title":"Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval","created":"2023-11-27","cited_by_count":4,"area":null},{"id":"2312.02803","title":"Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2402.16877","title":"Large Language Model Augmented Exercise Retrieval for Personalized Language Learning","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2406.12634","title":"News Without Borders: Domain Adaptation of Multilingual Sentence Embeddings for Cross-lingual News Recommendation","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2503.23239","title":"Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance","created":"2025-03-29","cited_by_count":4,"area":"synth"},{"id":"2211.01144","title":"UniASM: Binary Code Similarity Detection without Fine-tuning","created":"2022-10-28","cited_by_count":3,"area":null},{"id":"2212.08841","title":"AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation","created":"2022-12-17","cited_by_count":3,"area":null},{"id":"2311.00408","title":"AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2311.15563","title":"Noisy Self-Training with Synthetic Queries for Dense Retrieval","created":"2023-11-27","cited_by_count":3,"area":null},{"id":"2409.16570","title":"Disentangling Questions from Query Generation for Task-Adaptive Retrieval","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2409.20434","title":"QAEncoder: Towards Aligned Representation Learning in Question Answering Systems","created":"2024-09-30","cited_by_count":3,"area":"rag"},{"id":"2504.21015","title":"Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval","created":"2025-04-20","cited_by_count":3,"area":null},{"id":"2506.01877","title":"When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR","created":"2025-06-02","cited_by_count":3,"area":null},{"id":"2508.21632","title":"QZhou-Embedding Technical Report","created":"2025-08-29","cited_by_count":3,"area":null},{"id":"2511.08150","title":"DiffuGR: Generative Document Retrieval with Diffusion Language Models","created":"2025-11-11","cited_by_count":3,"area":"diffusion"},{"id":"2211.03988","title":"Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps","created":"2022-11-08","cited_by_count":2,"area":null},{"id":"2301.10521","title":"ExaRanker: Explanation-Augmented Neural Ranker","created":"2023-01-25","cited_by_count":2,"area":null},{"id":"2311.08533","title":"Natural Language Processing for Financial Regulation","created":"2023-11-14","cited_by_count":2,"area":null},{"id":"2504.07740","title":"Zero-Shot Cross-Domain Code Search without Fine-Tuning","created":"2025-04-10","cited_by_count":2,"area":null},{"id":"2505.23059","title":"From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval","created":"2025-05-29","cited_by_count":2,"area":"lr"},{"id":"2510.02241","title":"Study on LLMs for Promptagator-Style Dense Retriever Training","created":"2025-10-02","cited_by_count":2,"area":null},{"id":"2601.04646","title":"Succeeding at Scale: Enterprise Retrieval Benchmark Construction and Index-Preserving Query Adaptation for Multi-Tenant Search","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2608.16071","title":"Skill2Query: Exploiting Skill Structure to Generate Pseudo-Queries for Agent Skill Retrieval","created":"2026-08-17","cited_by_count":2,"area":"agents"},{"id":"2608.16502","title":"When Tool-Backed Skill Retrieval Fails: Source-Style Collapse in Executable Capability Retrieval","created":"2026-08-17","cited_by_count":2,"area":null},{"id":"2210.14463","title":"Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts","created":"2022-10-26","cited_by_count":1,"area":null},{"id":"2301.10517","title":"Multi-Tenant Optimization For Few-Shot Task-Oriented FAQ Retrieval","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2309.06131","title":"Annotating Data for Fine-Tuning a Neural Ranker? Current Active Learning Strategies are not Better than Random Selection","created":"2023-09-12","cited_by_count":1,"area":null},{"id":"2408.11189","title":"Emotional RAG LLMs: Reading Comprehension for the Open Internet","created":"2024-08-20","cited_by_count":1,"area":null},{"id":"2507.09601","title":"NMIXX: Domain-Adapted Neural Embeddings for Cross-Lingual eXploration of Finance","created":"2025-07-13","cited_by_count":1,"area":null},{"id":"2509.15234","title":"Exploring the Capabilities of Large Language Model Encoders for Image-Text Retrieval in Chest X-rays","created":"2025-09-17","cited_by_count":1,"area":null},{"id":"2509.16442","title":"Evaluating the Effectiveness and Scalability of LLM-Based Data Augmentation for Retrieval","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2511.05684","title":"A Representation Sharpening Framework for Zero Shot Dense Retrieval","created":"2025-11-07","cited_by_count":1,"area":null},{"id":"2402.02932","title":"Domain Adaptation of Multilingual Semantic Search -- Literature Review","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2402.16200","title":"IR2: Information Regularization for Information Retrieval","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2403.18671","title":"Fact Checking Beyond Training Set","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2405.11461","title":"DocReLM: Mastering Document Retrieval with Language Model","created":"2024-05-19","cited_by_count":0,"area":null},{"id":"2504.07228","title":"ConceptCarve: Dynamic Realization of Evidence","created":"2025-04-09","cited_by_count":0,"area":null},{"id":"2504.10250","title":"MURR: Model Updating with Regularized Replay for Searching a Document Stream","created":"2025-04-14","cited_by_count":0,"area":null},{"id":"2505.21010","title":"Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains","created":"2025-05-27","cited_by_count":0,"area":null}],"next_cursor":"100"}