{"total":145,"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":"2112.01488","title":"ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction","created":"2021-12-02","cited_by_count":476,"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":"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":"2109.10086","title":"SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval","created":"2021-09-21","cited_by_count":127,"area":null},{"id":"2108.08787","title":"Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval","created":"2021-08-19","cited_by_count":119,"area":null},{"id":"2112.07577","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","created":"2021-12-14","cited_by_count":119,"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":"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":"2205.09707","title":"PLAID: An Efficient Engine for Late Interaction Retrieval","created":"2022-05-19","cited_by_count":101,"area":null},{"id":"2205.04733","title":"From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective","created":"2022-05-10","cited_by_count":98,"area":null},{"id":"2403.06789","title":"SPLADE-v3: New baselines for SPLADE","created":"2024-03-11","cited_by_count":72,"area":null},{"id":"2106.14807","title":"A Few Brief Notes on DeepImpact, COIL, and a Conceptual Framework for Information Retrieval Techniques","created":"2021-06-28","cited_by_count":69,"area":null},{"id":"2209.14290","title":"FiD-Light: Efficient and Effective Retrieval-Augmented Text Generation","created":"2022-09-28","cited_by_count":63,"area":"rag"},{"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":"2204.13679","title":"Curriculum Learning for Dense Retrieval Distillation","created":"2022-04-28","cited_by_count":38,"area":null},{"id":"2104.05740","title":"A Replication Study of Dense Passage Retriever","created":"2021-04-12","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":"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":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2103.11920","title":"Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval","created":"2021-03-22","cited_by_count":28,"area":null},{"id":"2204.02363","title":"Towards Best Practices for Training Multilingual Dense Retrieval Models","created":"2022-04-05","cited_by_count":26,"area":null},{"id":"2207.03834","title":"An Efficiency Study for SPLADE Models","created":"2022-07-08","cited_by_count":26,"area":null},{"id":"2501.16214","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","created":"2025-01-27","cited_by_count":25,"area":"rag"},{"id":"2110.01529","title":"A Proposed Conceptual Framework for a Representational Approach to Information Retrieval","created":"2021-10-04","cited_by_count":24,"area":null},{"id":"2203.06169","title":"LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval","created":"2022-03-11","cited_by_count":24,"area":null},{"id":"2112.08723","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","created":"2021-12-16","cited_by_count":22,"area":null},{"id":"2204.00716","title":"CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos","created":"2022-04-01","cited_by_count":22,"area":null},{"id":"2602.15547","title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","created":"2026-02-17","cited_by_count":22,"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":"2209.13335","title":"PROD: Progressive Distillation for Dense Retrieval","created":"2022-09-27","cited_by_count":21,"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":"2404.14600","title":"Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding","created":"2024-04-22","cited_by_count":19,"area":null},{"id":"2204.00185","title":"Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings","created":"2022-04-01","cited_by_count":17,"area":"distill"},{"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":"2209.08754","title":"Toward Understanding Privileged Features Distillation in Learning-to-Rank","created":"2022-09-19","cited_by_count":16,"area":null},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16,"area":"distill"},{"id":"2208.13661","title":"LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval","created":"2022-08-29","cited_by_count":15,"area":null},{"id":"2301.12566","title":"Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation","created":"2023-01-29","cited_by_count":15,"area":null},{"id":"2402.11573","title":"BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models","created":"2024-02-18","cited_by_count":15,"area":"rag"},{"id":"2407.20750","title":"JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources","created":"2024-07-30","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":"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":"2302.02108","title":"Knowledge Distillation in Vision Transformers: A Critical Review","created":"2023-02-04","cited_by_count":13,"area":"distill"},{"id":"2504.01818","title":"Efficient Constant-Space Multi-Vector Retrieval","created":"2025-04-02","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":"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":"2112.07771","title":"Boosted Dense Retriever","created":"2021-12-14","cited_by_count":10,"area":null},{"id":"2204.11673","title":"Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking","created":"2022-04-25","cited_by_count":10,"area":null},{"id":"2205.00820","title":"Entity-aware Transformers for Entity Search","created":"2022-05-02","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":"2301.10576","title":"A Study on FGSM Adversarial Training for Neural Retrieval","created":"2023-01-25","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":"2504.10816","title":"CSPLADE: Learned Sparse Retrieval with Causal Language Models","created":"2025-04-15","cited_by_count":10,"area":null},{"id":"2204.11458","title":"ED2LM: Encoder-Decoder to Language Model for Faster Document Re-ranking Inference","created":"2022-04-25","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":"2408.11119","title":"Mistral-SPLADE: LLMs for better Learned Sparse Retrieval","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2410.17152","title":"Improving Pinterest Search Relevance Using Large Language Models","created":"2024-10-22","cited_by_count":8,"area":null},{"id":"2411.04403","title":"Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers","created":"2024-11-07","cited_by_count":8,"area":"distill"},{"id":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2110.02065","title":"SDR: Efficient Neural Re-ranking using Succinct Document Representation","created":"2021-10-03","cited_by_count":7,"area":null},{"id":"2403.00435","title":"Hierarchical Indexing for Retrieval-Augmented Opinion Summarization","created":"2024-03-01","cited_by_count":7,"area":"rag"},{"id":"2411.04602","title":"Self-Calibrated Listwise Reranking with Large Language Models","created":"2024-11-07","cited_by_count":7,"area":null},{"id":"2502.05364","title":"Hypencoder: Hypernetworks for Information Retrieval","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2510.11056","title":"From Reasoning LLMs to BERT: A Two-Stage Distillation Framework for Search Relevance","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2406.17968","title":"Efficient Document Ranking with Learnable Late Interactions","created":"2024-06-25","cited_by_count":6,"area":null},{"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":"2507.08336","title":"Distillation versus Contrastive Learning: How to Train Your Rerankers","created":"2025-07-11","cited_by_count":6,"area":"distill"},{"id":"2603.13277","title":"Learning Retrieval Models with Sparse Autoencoders","created":"2026-02-27","cited_by_count":6,"area":"mechinterp"},{"id":"2306.11550","title":"Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency","created":"2023-06-05","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":"2201.00365","title":"Establishing Strong Baselines for TripClick Health Retrieval","created":"2022-01-02","cited_by_count":4,"area":null},{"id":"2204.07023","title":"Composite Code Sparse Autoencoders for first stage retrieval","created":"2022-04-14","cited_by_count":4,"area":"mechinterp"},{"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":"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":"2212.10192","title":"Adam: Dense Retrieval Distillation with Adaptive Dark Examples","created":"2022-12-20","cited_by_count":4,"area":"distill"},{"id":"2403.05975","title":"Measuring Bias in a Ranked List using Term-based Representations","created":"2024-03-09","cited_by_count":4,"area":null},{"id":"2403.20222","title":"Shallow Cross-Encoders for Low-Latency Retrieval","created":"2024-03-29","cited_by_count":4,"area":null},{"id":"2407.07479","title":"How to Make Cross Encoder a Good Teacher for Efficient Image-Text Retrieval?","created":"2024-07-10","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":"2505.07105","title":"Knowledge Distillation for Enhancing Walmart E-commerce Search Relevance Using Large Language Models","created":"2025-05-11","cited_by_count":4,"area":"distill"},{"id":"2509.12539","title":"LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations","created":"2025-09-16","cited_by_count":4,"area":"distill"},{"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":"2205.03273","title":"Collective Relevance Labeling for Passage Retrieval","created":"2022-05-06","cited_by_count":3,"area":"distill"},{"id":"2211.00177","title":"Learning to Navigate Wikipedia by Taking Random Walks","created":"2022-10-31","cited_by_count":3,"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":"2304.14522","title":"Multivariate Representation Learning for Information Retrieval","created":"2023-04-27","cited_by_count":3,"area":null},{"id":"2312.16144","title":"Towards Better Monolingual Japanese Retrievers with Multi-Vector Models","created":"2023-12-26","cited_by_count":3,"area":null},{"id":"2403.03516","title":"Unsupervised Multilingual Dense Retrieval via Generative Pseudo Labeling","created":"2024-03-06","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":"2410.01383","title":"PairDistill: Pairwise Relevance Distillation for Dense Retrieval","created":"2024-10-02","cited_by_count":3,"area":null},{"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":"2202.12510","title":"Asyncval: A Toolkit for Asynchronously Validating Dense Retriever Checkpoints during Training","created":"2022-02-25","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":"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":"2305.02996","title":"Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition","created":"2023-05-04","cited_by_count":2,"area":null}],"next_cursor":"100"}