{"total":98,"rows":[{"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":"2403.06789","title":"SPLADE-v3: New baselines for SPLADE","created":"2024-03-11","cited_by_count":72,"area":null},{"id":"2309.15088","title":"RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models","created":"2023-09-26","cited_by_count":70,"area":null},{"id":"2210.17236","title":"When Language Model Meets Private Library","created":"2022-10-31","cited_by_count":54,"area":null},{"id":"2406.11678","title":"TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy","created":"2024-06-17","cited_by_count":47,"area":null},{"id":"2310.13243","title":"Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking","created":"2023-10-20","cited_by_count":44,"area":null},{"id":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31,"area":"rag"},{"id":"2305.07614","title":"NevIR: Negation in Neural Information Retrieval","created":"2023-05-12","cited_by_count":29,"area":null},{"id":"2406.14449","title":"APEER: Automatic Prompt Engineering Enhances Large Language Model Reranking","created":"2024-06-20","cited_by_count":28,"area":null},{"id":"2401.04810","title":"Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation","created":"2024-01-09","cited_by_count":22,"area":"distill"},{"id":"2409.17424","title":"Results of the Big ANN: NeurIPS'23 competition","created":"2024-09-25","cited_by_count":22,"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":"2404.18185","title":"Ranked List Truncation for Large Language Model-based Re-Ranking","created":"2024-04-28","cited_by_count":20,"area":null},{"id":"2205.11194","title":"UnifieR: A Unified Retriever for Large-Scale Retrieval","created":"2022-05-23","cited_by_count":19,"area":null},{"id":"2404.13556","title":"ChatRetriever: Adapting Large Language Models for Generalized and Robust Conversational Dense Retrieval","created":"2024-04-21","cited_by_count":19,"area":null},{"id":"2306.07471","title":"Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard","created":"2023-06-13","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":"2409.11598","title":"Towards Fair RAG: On the Impact of Fair Ranking in Retrieval-Augmented Generation","created":"2024-09-17","cited_by_count":15,"area":"rag"},{"id":"2506.22058","title":"Lost at the Beginning of Reasoning","created":"2025-06-27","cited_by_count":15,"area":"lr"},{"id":"2402.13350","title":"PIRB: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods","created":"2024-02-20","cited_by_count":14,"area":null},{"id":"2402.17535","title":"Multimodal Learned Sparse Retrieval with Probabilistic Expansion Control","created":"2024-02-27","cited_by_count":12,"area":null},{"id":"2410.19218","title":"Taxonomy-guided Semantic Indexing for Academic Paper Search","created":"2024-10-25","cited_by_count":12,"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":"2403.04160","title":"Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2301.10576","title":"A Study on FGSM Adversarial Training for Neural Retrieval","created":"2023-01-25","cited_by_count":10,"area":null},{"id":"2310.09536","title":"CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering","created":"2023-10-14","cited_by_count":10,"area":"rag"},{"id":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2305.13915","title":"DAPR: A Benchmark on Document-Aware Passage Retrieval","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9,"area":null},{"id":"2410.14609","title":"DiSCo: LLM Knowledge Distillation for Efficient Sparse Retrieval in Conversational Search","created":"2024-10-18","cited_by_count":9,"area":"distill"},{"id":"2510.00671","title":"Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector","created":"2025-10-01","cited_by_count":9,"area":null},{"id":"2408.11119","title":"Mistral-SPLADE: LLMs for better Learned Sparse Retrieval","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2505.18512","title":"AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking","created":"2025-05-24","cited_by_count":8,"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":"2502.05364","title":"Hypencoder: Hypernetworks for Information Retrieval","created":"2025-02-07","cited_by_count":7,"area":null},{"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":"2506.01673","title":"GRAM: Generative Recommendation via Semantic-aware Multi-granular Late Fusion","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2209.15469","title":"Zero-Shot Retrieval with Search Agents and Hybrid Environments","created":"2022-09-30","cited_by_count":6,"area":"agents"},{"id":"2404.05825","title":"LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2410.15262","title":"HyQE: Ranking Contexts with Hypothetical Query Embeddings","created":"2024-10-20","cited_by_count":6,"area":"rag"},{"id":"2506.04760","title":"Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2603.13277","title":"Learning Retrieval Models with Sparse Autoencoders","created":"2026-02-27","cited_by_count":6,"area":"mechinterp"},{"id":"2508.05512","title":"RankArena: A Unified Platform for Evaluating Retrieval, Reranking and RAG with Human and LLM Feedback","created":"2025-08-07","cited_by_count":5,"area":"rag"},{"id":"2601.01684","title":"LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum","created":"2026-01-04","cited_by_count":5,"area":null},{"id":"2603.18516","title":"Total Recall QA: A Verifiable Evaluation Suite for Deep Research Agents","created":"2026-03-19","cited_by_count":5,"area":"agents"},{"id":"2304.01019","title":"Simple Yet Effective Neural Ranking and Reranking Baselines for Cross-Lingual Information Retrieval","created":"2023-04-03","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":"2312.02429","title":"PEFA: Parameter-Free Adapters for Large-scale Embedding-based Retrieval Models","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2411.05508","title":"An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2504.07109","title":"OSCAR: Online Soft Compression And Reranking","created":"2025-03-17","cited_by_count":4,"area":"rag"},{"id":"2509.16621","title":"The Role of Vocabularies in Learning Sparse Representations for Ranking","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2510.22733","title":"E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2301.10444","title":"An Experimental Study on Pretraining Transformers from Scratch for IR","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2303.13220","title":"Parameter-Efficient Sparse Retrievers and Rerankers using Adapters","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2305.18494","title":"Adapting Learned Sparse Retrieval for Long Documents","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2401.11248","title":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval","created":"2024-01-20","cited_by_count":3,"area":null},{"id":"2402.14318","title":"Assessing generalization capability of text ranking models in Polish","created":"2024-02-22","cited_by_count":3,"area":"rag"},{"id":"2411.04539","title":"Best Practices for Distilling Large Language Models into BERT for Web Search Ranking","created":"2024-11-07","cited_by_count":3,"area":"distill"},{"id":"2503.18570","title":"Dense Retrieval for Low Resource Languages -- the Case of Amharic Language","created":"2025-03-24","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"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":"2305.14499","title":"NAIL: Lexical Retrieval Indices with Efficient Non-Autoregressive Decoders","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2412.01443","title":"Multi-Facet Blending for Faceted Query-by-Example Retrieval","created":"2024-12-02","cited_by_count":2,"area":null},{"id":"2504.01101","title":"Uncovering the Limitations of Query Performance Prediction: Failures, Insights, and Implications for Selective Query Processing","created":"2025-04-01","cited_by_count":2,"area":null},{"id":"2504.06609","title":"InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction Features","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2504.16264","title":"CLIRudit: Cross-Lingual Information Retrieval of Scientific Documents","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2509.08395","title":"SINDI: An Efficient Index for Sparse Vector Approximate Maximum Inner Product Search","created":"2025-09-10","cited_by_count":2,"area":"rag"},{"id":"2603.22008","title":"On the Challenges and Opportunities of Learned Sparse Retrieval for Code","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2604.27421","title":"A Reproducibility Study of LLM-Based Query Reformulation","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2608.02583","title":"UEmbed: Unified Sparse and Dense Multimodal Embeddings","created":"2026-08-03","cited_by_count":2,"area":"rag"},{"id":"2609.00638","title":"It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning","created":"2026-09-01","cited_by_count":2,"area":"lr"},{"id":"2302.02908","title":"LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2504.14839","title":"Exploring $\\ell_0$ Sparsification for Inference-free Sparse Retrievers","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2505.11900","title":"Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Data","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2509.24815","title":"Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2602.06526","title":"Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks","created":"2026-02-06","cited_by_count":1,"area":"agents"},{"id":"2603.24218","title":"Who Benefits from RAG? The Role of Exposure, Utility and Attribution Bias","created":"2026-03-25","cited_by_count":1,"area":"rag"},{"id":"2604.28142","title":"Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.29630","title":"Entity-Collision: A Stratified Protocol for Attributing Retrieval Lift in Agent Memory","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2608.11238","title":"Towards Query-Agnostic RAG Evaluation via Query Coverage and Claim Verifiability","created":"2026-07-31","cited_by_count":1,"area":"rag"},{"id":"2404.12152","title":"FecTek: Enhancing Term Weight in Lexicon-Based Retrieval with Feature Context and Term-level Knowledge","created":"2024-04-18","cited_by_count":0,"area":null},{"id":"2405.01924","title":"Semi-Parametric Retrieval via Binary Bag-of-Tokens Index","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2409.16198","title":"Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2410.18385","title":"Link, Synthesize, Retrieve: Universal Document Linking for Zero-Shot Information Retrieval","created":"2024-10-24","cited_by_count":0,"area":null},{"id":"2411.12921","title":"A Comparative Study of Text Retrieval Models on DaReCzech","created":"2024-11-19","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":"2601.00567","title":"Improving Scientific Document Retrieval with Academic Concept Index","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2604.21511","title":"From Tokens to Concepts: Leveraging SAE for SPLADE","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.17762","title":"Surface-Form Neural Sparse Retrieval: Robust Fuzzy Matching for Industrial Music Search","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.24556","title":"The Multilingual Curse at the Retrieval Layer: Evidence from Amharic","created":"2026-05-23","cited_by_count":0,"area":"rag"},{"id":"2606.11350","title":"When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval","created":"2026-06-09","cited_by_count":0,"area":"rag"},{"id":"2606.11945","title":"uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.00004","title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2608.26762","title":"Equal Ranking Quality, Different Decisions: Measuring and Reducing Order Dependence in LLM Scorers","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01316","title":"MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.01325","title":"VerTox: Verifiable Reward-Guided Corpus Poisoning Against Neural Ranking Models","created":"2026-09-01","cited_by_count":0,"area":"rag"},{"id":"2609.20050","title":"The Missing Complement: State-Conditioned Minimal Sufficient Evidence for Coding Agents","created":"2026-09-17","cited_by_count":0,"area":"agents"}],"next_cursor":null}