{"total":143,"rows":[{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253,"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":"2209.11755","title":"Promptagator: Few-shot Dense Retrieval From 8 Examples","created":"2022-09-23","cited_by_count":235,"area":null},{"id":"2303.07678","title":"Query2doc: Query Expansion with Large Language Models","created":"2023-03-14","cited_by_count":149,"area":null},{"id":"2307.11019","title":"Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentation","created":"2023-07-20","cited_by_count":147,"area":null},{"id":"2409.10173","title":"jina-embeddings-v3: Multilingual Embeddings With Task LoRA","created":"2024-09-16","cited_by_count":141,"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":"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":"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":"2210.10634","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","created":"2022-10-12","cited_by_count":115,"area":null},{"id":"2305.06984","title":"Evaluating Open-Domain Question Answering in the Era of Large Language Models","created":"2023-05-11","cited_by_count":111,"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":"2403.20327","title":"Gecko: Versatile Text Embeddings Distilled from Large Language Models","created":"2024-03-29","cited_by_count":83,"area":null},{"id":"2312.15503","title":"Llama2Vec: Unsupervised Adaptation of Large Language Models for Dense Retrieval","created":"2023-12-24","cited_by_count":78,"area":null},{"id":"2307.07164","title":"Learning to Retrieve In-Context Examples for Large Language Models","created":"2023-07-14","cited_by_count":60,"area":null},{"id":"2402.11457","title":"When Do LLMs Need Retrieval Augmentation? Mitigating LLMs' Overconfidence Helps Retrieval Augmentation","created":"2024-02-18","cited_by_count":59,"area":null},{"id":"2206.10128","title":"Bridging the Gap Between Indexing and Retrieval for Differentiable Search Index with Query Generation","created":"2022-06-21","cited_by_count":48,"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":"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":"2204.13679","title":"Curriculum Learning for Dense Retrieval Distillation","created":"2022-04-28","cited_by_count":38,"area":null},{"id":"2206.08063","title":"Towards Robust Ranker for Text Retrieval","created":"2022-06-16","cited_by_count":37,"area":null},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","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":"2305.07614","title":"NevIR: Negation in Neural Information Retrieval","created":"2023-05-12","cited_by_count":29,"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":"2311.05800","title":"Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval","created":"2023-11-10","cited_by_count":24,"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":"2204.12755","title":"A Thorough Examination on Zero-shot Dense Retrieval","created":"2022-04-27","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":"2210.11773","title":"SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval","created":"2022-10-21","cited_by_count":21,"area":null},{"id":"2205.10569","title":"HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking","created":"2022-05-21","cited_by_count":20,"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":"2408.12503","title":"The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design","created":"2024-08-22","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":"2508.03555","title":"PyLate: Flexible Training and Retrieval for Late Interaction Models","created":"2025-08-05","cited_by_count":18,"area":null},{"id":"2208.07670","title":"ConTextual Masked Auto-Encoder for Dense Passage Retrieval","created":"2022-08-16","cited_by_count":16,"area":null},{"id":"2509.09498","title":"SEDM: Selective Self-Evolving Distributed Memory for Agents","created":"2025-09-11","cited_by_count":16,"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":"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":"2502.21024","title":"TempRetriever: Fusion-based Temporal Dense Passage Retrieval for Time-Sensitive Questions","created":"2025-02-28","cited_by_count":15,"area":null},{"id":"2304.13649","title":"A Symmetric Dual Encoding Dense Retrieval Framework for Knowledge-Intensive Visual Question Answering","created":"2023-04-26","cited_by_count":14,"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":"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":"2305.05486","title":"MAUPQA: Massive Automatically-created Polish Question Answering Dataset","created":"2023-05-09","cited_by_count":11,"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":"2310.04678","title":"DORIS-MAE: Scientific Document Retrieval using Multi-level Aspect-based Queries","created":"2023-10-07","cited_by_count":11,"area":null},{"id":"2401.10487","title":"Generative Dense Retrieval: Memory Can Be a Burden","created":"2024-01-19","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":"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":"2208.11503","title":"DPTDR: Deep Prompt Tuning for Dense Passage Retrieval","created":"2022-08-24","cited_by_count":10,"area":null},{"id":"2210.05423","title":"Learning to Locate Visual Answer in Video Corpus Using Question","created":"2022-10-11","cited_by_count":10,"area":null},{"id":"2210.07564","title":"Q-TOD: A Query-driven Task-oriented Dialogue System","created":"2022-10-14","cited_by_count":10,"area":null},{"id":"2502.17057","title":"ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance","created":"2025-02-24","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":"2212.09598","title":"Query-as-context Pre-training for Dense Passage Retrieval","created":"2022-12-19","cited_by_count":9,"area":null},{"id":"2209.00218","title":"Isotropic Representation Can Improve Dense Retrieval","created":"2022-09-01","cited_by_count":8,"area":null},{"id":"2305.03276","title":"Expository Text Generation: Imitate, Retrieve, Paraphrase","created":"2023-05-05","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":"2408.11119","title":"Mistral-SPLADE: LLMs for better Learned Sparse Retrieval","created":"2024-08-20","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":"2205.12680","title":"Optimizing Test-Time Query Representations for Dense Retrieval","created":"2022-05-25","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":"2212.08897","title":"PolQA: Polish Question Answering Dataset","created":"2022-12-17","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":"2308.08285","title":"Pre-training with Large Language Model-based Document Expansion for Dense Passage Retrieval","created":"2023-08-16","cited_by_count":7,"area":null},{"id":"2411.04602","title":"Self-Calibrated Listwise Reranking with Large Language Models","created":"2024-11-07","cited_by_count":7,"area":null},{"id":"2212.10528","title":"HYRR: Hybrid Infused Reranking for Passage Retrieval","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2306.10348","title":"Typo-Robust Representation Learning for Dense Retrieval","created":"2023-06-17","cited_by_count":6,"area":null},{"id":"2310.08840","title":"Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogue","created":"2023-10-13","cited_by_count":6,"area":null},{"id":"2406.17968","title":"Efficient Document Ranking with Learnable Late Interactions","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2408.03402","title":"ULLME: A Unified Framework for Large Language Model Embeddings with Generation-Augmented Learning","created":"2024-08-06","cited_by_count":6,"area":null},{"id":"2411.12235","title":"BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?","created":"2024-11-19","cited_by_count":6,"area":null},{"id":"2607.27178","title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","created":"2026-07-29","cited_by_count":6,"area":null},{"id":"2208.00231","title":"Masked Autoencoders As The Unified Learners For Pre-Trained Sentence Representation","created":"2022-07-30","cited_by_count":5,"area":null},{"id":"2210.17167","title":"Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives","created":"2022-10-31","cited_by_count":5,"area":null},{"id":"2303.15311","title":"Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining","created":"2023-03-27","cited_by_count":5,"area":null},{"id":"2304.03158","title":"CoT-MAE v2: Contextual Masked Auto-Encoder with Multi-view Modeling for Passage Retrieval","created":"2023-04-05","cited_by_count":5,"area":null},{"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":"2309.08469","title":"Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering","created":"2023-09-15","cited_by_count":5,"area":null},{"id":"2310.09696","title":"Progressive Evidence Refinement for Open-domain Multimodal Retrieval Question Answering","created":"2023-10-15","cited_by_count":5,"area":null},{"id":"2311.03798","title":"Noisy Pair Corrector for Dense Retrieval","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2412.12505","title":"DocFusion: A Unified Framework for Document Parsing Tasks","created":"2024-12-17","cited_by_count":5,"area":null},{"id":"2504.05216","title":"Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling","created":"2025-04-07","cited_by_count":5,"area":null},{"id":"2505.17552","title":"Universal Biological Sequence Reranking for Improved De Novo Peptide Sequencing","created":"2025-05-23","cited_by_count":5,"area":null},{"id":"2112.08766","title":"CODER: An efficient framework for improving retrieval through COntextual Document Embedding Reranking","created":"2021-12-16","cited_by_count":4,"area":null},{"id":"2206.13974","title":"Joint Generator-Ranker Learning for Natural Language Generation","created":"2022-06-28","cited_by_count":4,"area":null},{"id":"2208.04232","title":"Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval","created":"2022-08-08","cited_by_count":4,"area":null},{"id":"2210.15133","title":"Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2212.01340","title":"Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking","created":"2022-12-02","cited_by_count":4,"area":null},{"id":"2212.09114","title":"CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion","created":"2022-12-18","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":"2312.02803","title":"Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic","created":"2023-12-05","cited_by_count":4,"area":null},{"id":"2401.00165","title":"Mitigating the Impact of False Negatives in Dense Retrieval with Contrastive Confidence Regularization","created":"2023-12-30","cited_by_count":4,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","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":"2305.13197","title":"Challenging Decoder helps in Masked Auto-Encoder Pre-training for Dense Passage Retrieval","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2305.17371","title":"Towards Better Entity Linking with Multi-View Enhanced Distillation","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2310.08877","title":"Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System","created":"2023-10-13","cited_by_count":3,"area":null}],"next_cursor":"100"}