{"total":113,"rows":[{"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":"2104.07186","title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List","created":"2021-04-15","cited_by_count":113,"area":null},{"id":"2406.15319","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","created":"2024-06-21","cited_by_count":108,"area":"rag"},{"id":"2211.09260","title":"Task-aware Retrieval with Instructions","created":"2022-11-16","cited_by_count":107,"area":null},{"id":"2110.03611","title":"Adversarial Retriever-Ranker for dense text retrieval","created":"2021-10-07","cited_by_count":83,"area":null},{"id":"2101.05667","title":"The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models","created":"2021-01-14","cited_by_count":81,"area":null},{"id":"2403.15246","title":"FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions","created":"2024-03-22","cited_by_count":69,"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":"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":"2205.01230","title":"Retrieval-Enhanced Machine Learning","created":"2022-05-02","cited_by_count":47,"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":"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":"2305.11694","title":"QUEST: A Retrieval Dataset of Entity-Seeking Queries with Implicit Set Operations","created":"2023-05-19","cited_by_count":31,"area":null},{"id":"2308.09861","title":"Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method","created":"2023-08-19","cited_by_count":29,"area":null},{"id":"2403.05676","title":"PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design","created":"2024-03-08","cited_by_count":28,"area":"rag"},{"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":"2104.09791","title":"B-PROP: Bootstrapped Pre-training with Representative Words Prediction for Ad-hoc Retrieval","created":"2021-04-20","cited_by_count":25,"area":"synth"},{"id":"2112.11031","title":"On Cross-Lingual Retrieval with Multilingual Text Encoders","created":"2021-12-21","cited_by_count":22,"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":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","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":"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":"2209.01335","title":"Neural Approaches to Multilingual Information Retrieval","created":"2022-09-03","cited_by_count":18,"area":null},{"id":"2312.15450","title":"Agent4Ranking: Semantic Robust Ranking via Personalized Query Rewriting Using Multi-agent LLM","created":"2023-12-24","cited_by_count":18,"area":"agents"},{"id":"2102.11903","title":"Neural ranking models for document retrieval","created":"2021-02-23","cited_by_count":16,"area":null},{"id":"2505.10413","title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","created":"2025-05-15","cited_by_count":16,"area":"rag"},{"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":"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":"2403.18276","title":"RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers","created":"2024-03-27","cited_by_count":15,"area":"ssm"},{"id":"2406.19760","title":"Learning Interpretable Legal Case Retrieval via Knowledge-Guided Case Reformulation","created":"2024-06-28","cited_by_count":15,"area":null},{"id":"2204.11989","title":"C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval","created":"2022-04-25","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":"2308.16753","title":"Context Aware Query Rewriting for Text Rankers using LLM","created":"2023-08-31","cited_by_count":14,"area":null},{"id":"2404.01574","title":"Multi-granular Adversarial Attacks against Black-box Neural Ranking Models","created":"2024-04-02","cited_by_count":14,"area":null},{"id":"2404.04163","title":"Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval","created":"2024-04-05","cited_by_count":13,"area":null},{"id":"2503.19174","title":"AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL","created":"2025-03-24","cited_by_count":13,"area":null},{"id":"2301.04283","title":"MGeo: Multi-Modal Geographic Pre-Training Method","created":"2023-01-11","cited_by_count":12,"area":null},{"id":"2301.12005","title":"EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval","created":"2023-01-27","cited_by_count":11,"area":"distill"},{"id":"2501.01832","title":"Time Series Language Model for Descriptive Caption Generation","created":"2025-01-03","cited_by_count":11,"area":null},{"id":"2105.09816","title":"Intra-Document Cascading: Learning to Select Passages for Neural Document Ranking","created":"2021-05-20","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":"2412.14354","title":"State Space Models are Strong Text Rerankers","created":"2024-12-18","cited_by_count":10,"area":"ssm"},{"id":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2205.04275","title":"Long Document Re-ranking with Modular Re-ranker","created":"2022-05-09","cited_by_count":9,"area":null},{"id":"2205.01886","title":"P^3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning","created":"2022-05-04","cited_by_count":7,"area":null},{"id":"2212.07841","title":"MASTER: Multi-task Pre-trained Bottlenecked Masked Autoencoders are Better Dense Retrievers","created":"2022-12-15","cited_by_count":7,"area":null},{"id":"2312.10329","title":"Perturbation-Invariant Adversarial Training for Neural Ranking Models: Improving the Effectiveness-Robustness Trade-Off","created":"2023-12-16","cited_by_count":7,"area":null},{"id":"2602.21456","title":"Revisiting Text Ranking in Deep Research","created":"2026-02-25","cited_by_count":7,"area":null},{"id":"2109.09057","title":"Knowledge-Enhanced Evidence Retrieval for Counterargument Generation","created":"2021-09-19","cited_by_count":6,"area":null},{"id":"2211.10841","title":"SeDR: Segment Representation Learning for Long Documents Dense Retrieval","created":"2022-11-20","cited_by_count":6,"area":null},{"id":"2306.03411","title":"Generate-then-Retrieve: Intent-Aware FAQ Retrieval in Product Search","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2412.18770","title":"Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models","created":"2024-12-25","cited_by_count":6,"area":"lr"},{"id":"2509.07253","title":"Benchmarking Information Retrieval Models on Complex Retrieval Tasks","created":"2025-09-08","cited_by_count":6,"area":null},{"id":"2201.04458","title":"Diagnosing BERT with Retrieval Heuristics","created":"2022-01-12","cited_by_count":5,"area":null},{"id":"2304.04099","title":"Unsupervised Story Discovery from Continuous News Streams via Scalable Thematic Embedding","created":"2023-04-08","cited_by_count":5,"area":null},{"id":"2401.05939","title":"DREQ: Document Re-Ranking Using Entity-based Query Understanding","created":"2024-01-11","cited_by_count":5,"area":null},{"id":"2504.06356","title":"Query Understanding in LLM-based Conversational Information Seeking","created":"2025-04-08","cited_by_count":5,"area":null},{"id":"2506.22141","title":"DAPFAM: A Domain-Aware Family-level Dataset to benchmark cross domain patent retrieval","created":"2025-06-27","cited_by_count":5,"area":null},{"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":"2109.01628","title":"Cross-Lingual Training with Dense Retrieval for Document Retrieval","created":"2021-09-03","cited_by_count":4,"area":null},{"id":"2205.12643","title":"Asking the Right Questions in Low Resource Template Extraction","created":"2022-05-25","cited_by_count":4,"area":null},{"id":"2212.10192","title":"Adam: Dense Retrieval Distillation with Adaptive Dark Examples","created":"2022-12-20","cited_by_count":4,"area":"distill"},{"id":"2212.10448","title":"Parameter-efficient Zero-shot Transfer for Cross-Language Dense Retrieval with Adapters","created":"2022-12-20","cited_by_count":4,"area":null},{"id":"2406.11391","title":"P-TA: Using Proximal Policy Optimization to Enhance Tabular Data Augmentation via Large Language Models","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2102.06815","title":"Exploring Classic and Neural Lexical Translation Models for Information Retrieval: Interpretability, Effectiveness, and Efficiency Benefits","created":"2021-02-12","cited_by_count":3,"area":null},{"id":"2108.06279","title":"On Single and Multiple Representations in Dense Passage Retrieval","created":"2021-08-13","cited_by_count":3,"area":null},{"id":"2108.13300","title":"Deep Natural Language Processing for LinkedIn Search","created":"2021-08-16","cited_by_count":3,"area":null},{"id":"2111.13611","title":"Predicting Document Coverage for Relation Extraction","created":"2021-11-26","cited_by_count":3,"area":null},{"id":"2306.04787","title":"Absformer: Transformer-based Model for Unsupervised Multi-Document Abstractive Summarization","created":"2023-06-07","cited_by_count":3,"area":null},{"id":"2405.00975","title":"PLAID SHIRTTT for Large-Scale Streaming Dense Retrieval","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2405.00977","title":"Distillation for Multilingual Information Retrieval","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2501.07111","title":"ListConRanker: A Contrastive Text Reranker with Listwise Encoding","created":"2025-01-13","cited_by_count":3,"area":"rag"},{"id":"2108.05652","title":"Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm","created":"2021-08-12","cited_by_count":2,"area":null},{"id":"2205.14226","title":"Fast and Light-Weight Answer Text Retrieval in Dialogue Systems","created":"2022-05-27","cited_by_count":2,"area":null},{"id":"2207.01262","title":"Positional Bias in Long-Document Ranking: Impact, Assessment, and Mitigation","created":"2022-07-04","cited_by_count":2,"area":null},{"id":"2209.06583","title":"Pre-training for Information Retrieval: Are Hyperlinks Fully Explored?","created":"2022-09-14","cited_by_count":2,"area":null},{"id":"2405.20994","title":"CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2104.09393","title":"Improving Transformer-Kernel Ranking Model Using Conformer and Query Term Independence","created":"2021-04-19","cited_by_count":1,"area":null},{"id":"2109.04611","title":"Query-driven Segment Selection for Ranking Long Documents","created":"2021-09-10","cited_by_count":1,"area":null},{"id":"2211.15324","title":"Low-resource Personal Attribute Prediction from Conversation","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2212.05225","title":"LEAD: Liberal Feature-based Distillation for Dense Retrieval","created":"2022-12-10","cited_by_count":1,"area":"distill"},{"id":"2402.11757","title":"Large Language Models for Stemming: Promises, Pitfalls and Failures","created":"2024-02-19","cited_by_count":1,"area":null},{"id":"2404.08118","title":"HLTCOE at TREC 2023 NeuCLIR Track","created":"2024-04-11","cited_by_count":1,"area":null},{"id":"2409.01357","title":"Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domain","created":"2024-09-02","cited_by_count":1,"area":null},{"id":"2510.11589","title":"QDER: Query-Specific Document and Entity Representations for Multi-Vector Document Re-Ranking","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2511.16600","title":"You Only Forward Once: An Efficient Compositional Judging Paradigm","created":"2025-11-20","cited_by_count":1,"area":"mllm"},{"id":"2512.23307","title":"RobustMask: Certified Robustness against Adversarial Neural Ranking Attack via Randomized Masking","created":"2025-12-29","cited_by_count":1,"area":"rag"},{"id":"2601.00691","title":"TeleDoCTR: Domain-Specific and Contextual Troubleshooting for Telecommunications","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2108.08252","title":"Deep Natural Language Processing for LinkedIn Search Systems","created":"2021-07-30","cited_by_count":0,"area":null},{"id":"2109.00729","title":"ConQX: Semantic Expansion of Spoken Queries for Intent Detection based on Conditioned Text Generation","created":"2021-09-02","cited_by_count":0,"area":null},{"id":"2111.05988","title":"Cross-language Information Retrieval","created":"2021-11-10","cited_by_count":0,"area":null},{"id":"2112.07618","title":"Robust Information Retrieval for False Claims with Distracting Entities In Fact Extraction and Verification","created":"2021-12-10","cited_by_count":0,"area":null},{"id":"2203.06408","title":"Information retrieval for label noise document ranking by bag sampling and group-wise loss","created":"2022-03-12","cited_by_count":0,"area":null},{"id":"2211.14450","title":"Text-Aware Dual Routing Network for Visual Question Answering","created":"2022-11-17","cited_by_count":0,"area":null},{"id":"2212.07126","title":"Explainability of Text Processing and Retrieval Methods: A Survey","created":"2022-12-14","cited_by_count":0,"area":null},{"id":"2307.00370","title":"Improving Text Matching in E-Commerce Search with A Rationalizable, Intervenable and Fast Entity-Based Relevance Model","created":"2023-07-01","cited_by_count":0,"area":null},{"id":"2310.06626","title":"Topic-DPR: Topic-based Prompts for Dense Passage Retrieval","created":"2023-10-10","cited_by_count":0,"area":null}],"next_cursor":"100"}