{"total":38,"rows":[{"id":"2104.08663","title":"BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models","created":"2021-04-17","cited_by_count":1252,"area":null},{"id":"2108.13897","title":"mMARCO: A Multilingual Version of the MS MARCO Passage Ranking Dataset","created":"2021-08-31","cited_by_count":116,"area":null},{"id":"2205.12487","title":"End-to-End Multimodal Fact-Checking and Explanation Generation: A Challenging Dataset and Models","created":"2022-05-25","cited_by_count":107,"area":null},{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104,"area":null},{"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":"2110.06918","title":"Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?","created":"2021-10-13","cited_by_count":60,"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":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2203.08745","title":"Multi-Stage Prompting for Knowledgeable Dialogue Generation","created":"2022-03-16","cited_by_count":22,"area":null},{"id":"2110.08395","title":"DS-TOD: Efficient Domain Specialization for Task Oriented Dialog","created":"2021-10-15","cited_by_count":21,"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":"2305.18144","title":"GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking","created":"2023-05-29","cited_by_count":11,"area":null},{"id":"2104.07198","title":"Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2205.09278","title":"Modeling Exemplification in Long-form Question Answering via Retrieval","created":"2022-05-19","cited_by_count":7,"area":null},{"id":"2210.06349","title":"Context Generation Improves Open Domain Question Answering","created":"2022-10-12","cited_by_count":7,"area":null},{"id":"2312.14106","title":"Learning Human-like Representations to Enable Learning Human Values","created":"2023-12-21","cited_by_count":7,"area":null},{"id":"2212.03222","title":"LawngNLI: A Long-Premise Benchmark for In-Domain Generalization from Short to Long Contexts and for Implication-Based Retrieval","created":"2022-12-06","cited_by_count":6,"area":null},{"id":"2511.22150","title":"From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2201.09651","title":"Artefact Retrieval: Overview of NLP Models with Knowledge Base Access","created":"2022-01-24","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":"2606.11780","title":"What Limits Does Quantization Place on Dense Top-$k$ Retrieval? A Theoretical Study","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2209.05452","title":"Large-scale Evaluation of Transformer-based Article Encoders on the Task of Citation Recommendation","created":"2022-09-12","cited_by_count":3,"area":null},{"id":"2105.04024","title":"DocSCAN: Unsupervised Text Classification via Learning from Neighbors","created":"2021-05-09","cited_by_count":2,"area":null},{"id":"2406.09288","title":"Large Language Model as a Teacher for Zero-shot Tagging at Extreme Scales","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2410.23510","title":"Tiny Transformers Excel at Sentence Compression","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2204.09481","title":"Unsupervised Ranking and Aggregation of Label Descriptions for Zero-Shot Classifiers","created":"2022-04-20","cited_by_count":1,"area":null},{"id":"2210.13678","title":"Bridging the Training-Inference Gap for Dense Phrase Retrieval","created":"2022-10-25","cited_by_count":1,"area":null},{"id":"2401.04732","title":"A case study of Generative AI in MSX Sales Copilot: Improving seller productivity with a real-time question-answering system for content recommendation","created":"2024-01-04","cited_by_count":1,"area":null},{"id":"2402.12997","title":"Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2411.12880","title":"Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Events","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2506.17934","title":"A GenAI System for Improved FAIR Independent Biological Database Integration","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2605.24938","title":"Your Embedding Model is SMARTer Than You Think","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2410.21054","title":"Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modeling","created":"2024-10-28","cited_by_count":0,"area":null},{"id":"2412.10313","title":"MST-R: Multi-Stage Tuning for Retrieval Systems and Metric Evaluation","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2505.13550","title":"JIR-Arena: The First Benchmark Dataset for Just-in-time Information Recommendation","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2601.20844","title":"$\\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.23753","title":"SeedER: Seed-Expand-Retrieve for Efficient Knowledge Graph Retrieval","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2609.23971","title":"UniK: Universal Knowledge Perception for Digital and Physical AI","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}