{"total":177,"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":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216,"area":null},{"id":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476,"area":null},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456,"area":null},{"id":"2104.06967","title":"Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling","created":"2021-04-14","cited_by_count":238,"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":"2108.05540","title":"Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval","created":"2021-08-12","cited_by_count":203,"area":null},{"id":"2110.07367","title":"RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking","created":"2021-10-14","cited_by_count":176,"area":null},{"id":"2104.08253","title":"Condenser: a Pre-training Architecture for Dense Retrieval","created":"2021-04-16","cited_by_count":162,"area":null},{"id":"2105.02605","title":"GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph","created":"2021-05-06","cited_by_count":143,"area":null},{"id":"2102.08473","title":"COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining","created":"2021-02-16","cited_by_count":126,"area":null},{"id":"2205.12035","title":"RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder","created":"2022-05-24","cited_by_count":118,"area":null},{"id":"2104.07186","title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List","created":"2021-04-15","cited_by_count":113,"area":null},{"id":"2404.14851","title":"From Matching to Generation: A Survey on Generative Information Retrieval","created":"2024-04-23","cited_by_count":89,"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":"2303.10868","title":"Retrieving Multimodal Information for Augmented Generation: A Survey","created":"2023-03-20","cited_by_count":85,"area":null},{"id":"2110.03611","title":"Adversarial Retriever-Ranker for dense text retrieval","created":"2021-10-07","cited_by_count":83,"area":null},{"id":"2112.08558","title":"CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning","created":"2021-12-16","cited_by_count":68,"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":"2112.09924","title":"The Web Is Your Oyster - Knowledge-Intensive NLP against a Very Large Web Corpus","created":"2021-12-18","cited_by_count":60,"area":null},{"id":"2108.06027","title":"PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval","created":"2021-08-13","cited_by_count":50,"area":null},{"id":"2108.13454","title":"Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback","created":"2021-08-30","cited_by_count":47,"area":null},{"id":"2206.10658","title":"Questions Are All You Need to Train a Dense Passage Retriever","created":"2022-06-21","cited_by_count":47,"area":null},{"id":"2112.07708","title":"Learning to Retrieve Passages without Supervision","created":"2021-12-14","cited_by_count":46,"area":null},{"id":"2101.00117","title":"Multi-task Retrieval for Knowledge-Intensive Tasks","created":"2021-01-01","cited_by_count":44,"area":null},{"id":"2404.03302","title":"How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?","created":"2024-04-04","cited_by_count":44,"area":null},{"id":"2104.08445","title":"Joint Passage Ranking for Diverse Multi-Answer Retrieval","created":"2021-04-17","cited_by_count":43,"area":null},{"id":"2201.05176","title":"Neural Approaches to Conversational Information Retrieval","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2203.08372","title":"Multi-View Document Representation Learning for Open-Domain Dense Retrieval","created":"2022-03-16","cited_by_count":41,"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":"2104.06245","title":"Understanding Hard Negatives in Noise Contrastive Estimation","created":"2021-04-13","cited_by_count":39,"area":null},{"id":"2204.13679","title":"Curriculum Learning for Dense Retrieval Distillation","created":"2022-04-28","cited_by_count":38,"area":null},{"id":"2109.03502","title":"R2-D2: A Modular Baseline for Open-Domain Question Answering","created":"2021-09-08","cited_by_count":37,"area":null},{"id":"2206.08063","title":"Towards Robust Ranker for Text Retrieval","created":"2022-06-16","cited_by_count":37,"area":null},{"id":"2209.06506","title":"Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models","created":"2022-09-14","cited_by_count":37,"area":null},{"id":"2111.08366","title":"Multi-Vector Models with Textual Guidance for Fine-Grained Scientific Document Similarity","created":"2021-11-16","cited_by_count":35,"area":null},{"id":"2109.08133","title":"Phrase Retrieval Learns Passage Retrieval, Too","created":"2021-09-16","cited_by_count":33,"area":null},{"id":"2207.04452","title":"NGAME: Negative Mining-aware Mini-batching for Extreme Classification","created":"2022-07-10","cited_by_count":32,"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":"2109.01156","title":"Challenges in Generalization in Open Domain Question Answering","created":"2021-09-02","cited_by_count":30,"area":null},{"id":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2110.07581","title":"Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations","created":"2021-10-14","cited_by_count":27,"area":null},{"id":"2203.03367","title":"Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval","created":"2022-03-07","cited_by_count":27,"area":null},{"id":"2210.04873","title":"CORE: A Retrieve-then-Edit Framework for Counterfactual Data Generation","created":"2022-10-10","cited_by_count":24,"area":null},{"id":"2203.13088","title":"Introducing Neural Bag of Whole-Words with ColBERTer: Contextualized Late Interactions using Enhanced Reduction","created":"2022-03-24","cited_by_count":21,"area":null},{"id":"2204.12785","title":"Plug-and-Play Adaptation for Continuously-updated QA","created":"2022-04-27","cited_by_count":21,"area":null},{"id":"2210.11773","title":"SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2211.07886","title":"A Survey for Efficient Open Domain Question Answering","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2311.04335","title":"Sub-Sentence Encoder: Contrastive Learning of Propositional Semantic Representations","created":"2023-11-07","cited_by_count":20,"area":null},{"id":"2403.00784","title":"Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges","created":"2024-02-18","cited_by_count":20,"area":null},{"id":"2105.12936","title":"Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence","created":"2021-05-27","cited_by_count":19,"area":null},{"id":"2211.10411","title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval","created":"2022-11-18","cited_by_count":19,"area":null},{"id":"2206.14719","title":"Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision","created":"2022-06-29","cited_by_count":18,"area":null},{"id":"2112.07381","title":"You Only Need One Model for Open-domain Question Answering","created":"2021-12-14","cited_by_count":17,"area":null},{"id":"2210.05197","title":"Mixed-modality Representation Learning and Pre-training for Joint Table-and-Text Retrieval in OpenQA","created":"2022-10-11","cited_by_count":17,"area":null},{"id":"2310.04475","title":"Demystifying Embedding Spaces using Large Language Models","created":"2023-10-06","cited_by_count":17,"area":null},{"id":"2311.14740","title":"AutoKG: Efficient Automated Knowledge Graph Generation for Language Models","created":"2023-11-22","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":"2208.13661","title":"LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval","created":"2022-08-29","cited_by_count":15,"area":null},{"id":"2305.17080","title":"Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering","created":"2023-05-26","cited_by_count":15,"area":null},{"id":"2105.03599","title":"Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval","created":"2021-05-08","cited_by_count":14,"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":"2210.05043","title":"Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling","created":"2022-10-10","cited_by_count":14,"area":null},{"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":"2407.01965","title":"AdaCQR: Enhancing Query Reformulation for Conversational Search via Sparse and Dense Retrieval Alignment","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2301.13310","title":"Alternating Updates for Efficient Transformers","created":"2023-01-30","cited_by_count":13,"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":"2211.01267","title":"Multi-Vector Retrieval as Sparse Alignment","created":"2022-11-02","cited_by_count":12,"area":null},{"id":"2307.08303","title":"Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models","created":"2023-07-17","cited_by_count":12,"area":null},{"id":"2307.10323","title":"IncDSI: Incrementally Updatable Document Retrieval","created":"2023-07-19","cited_by_count":12,"area":null},{"id":"2411.00489","title":"Human-inspired Perspectives: A Survey on AI Long-term Memory","created":"2024-11-01","cited_by_count":12,"area":null},{"id":"2510.05038","title":"Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization","created":"2025-10-06","cited_by_count":12,"area":null},{"id":"2207.06220","title":"Improving Wikipedia Verifiability with AI","created":"2022-07-08","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":"2101.06980","title":"Mitigating the Position Bias of Transformer Models in Passage Re-Ranking","created":"2021-01-18","cited_by_count":10,"area":null},{"id":"2112.07771","title":"Boosted Dense Retriever","created":"2021-12-14","cited_by_count":10,"area":null},{"id":"2208.11503","title":"DPTDR: Deep Prompt Tuning for Dense Passage Retrieval","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2210.12579","title":"Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization","created":"2022-10-23","cited_by_count":10,"area":null},{"id":"2305.09025","title":"Soft Prompt Decoding for Multilingual Dense Retrieval","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2505.21815","title":"Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking","created":"2025-05-27","cited_by_count":10,"area":null},{"id":"2301.12847","title":"Finding the Law: Enhancing Statutory Article Retrieval via Graph Neural Networks","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2204.08173","title":"TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval","created":"2022-04-18","cited_by_count":8,"area":null},{"id":"2312.05417","title":"ESPN: Memory-Efficient Multi-Vector Information Retrieval","created":"2023-12-09","cited_by_count":8,"area":null},{"id":"2404.00684","title":"Generative Retrieval as Multi-Vector Dense Retrieval","created":"2024-03-31","cited_by_count":8,"area":null},{"id":"2406.00247","title":"Large Language Models for Relevance Judgment in Product Search","created":"2024-06-01","cited_by_count":8,"area":null},{"id":"2406.03283","title":"CATCODER: Repository-Level Code Generation with Relevant Code and Type Context","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2408.17344","title":"rerankers: A Lightweight Python Library to Unify Ranking Methods","created":"2024-08-30","cited_by_count":8,"area":null},{"id":"2411.11767","title":"Drowning in Documents: Consequences of Scaling Reranker Inference","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2509.10697","title":"A Survey on Retrieval And Structuring Augmented Generation with Large Language Models","created":"2025-09-12","cited_by_count":8,"area":null},{"id":"2102.09206","title":"Less is More: Pre-train a Strong Text Encoder for Dense Retrieval Using a Weak Decoder","created":"2021-02-18","cited_by_count":7,"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":"2201.05409","title":"Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval","created":"2022-01-14","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":"2210.01371","title":"A Study on the Efficiency and Generalization of Light Hybrid Retrievers","created":"2022-10-04","cited_by_count":7,"area":null},{"id":"2305.06557","title":"Long-Tailed Question Answering in an Open World","created":"2023-05-11","cited_by_count":7,"area":null},{"id":"2310.10636","title":"Dual-Encoders for Extreme Multi-Label Classification","created":"2023-10-16","cited_by_count":7,"area":null},{"id":"2407.17631","title":"BLAZE: Cross-Language and Cross-Project Bug Localization via Dynamic Chunking and Hard Example Learning","created":"2024-07-24","cited_by_count":7,"area":null},{"id":"2110.10778","title":"Contrastive Document Representation Learning with Graph Attention Networks","created":"2021-10-20","cited_by_count":6,"area":null},{"id":"2210.02068","title":"Nonparametric Decoding for Generative Retrieval","created":"2022-10-05","cited_by_count":6,"area":null},{"id":"2211.00915","title":"Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models","created":"2022-11-02","cited_by_count":6,"area":null}],"next_cursor":"100"}