{"total":147,"rows":[{"id":"2212.03533","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","created":"2022-12-07","cited_by_count":1253,"area":null},{"id":"2112.09118","title":"Unsupervised Dense Information Retrieval with Contrastive Learning","created":"2021-12-16","cited_by_count":1216,"area":null},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723,"area":null},{"id":"2205.13147","title":"Matryoshka Representation Learning","created":"2022-05-26","cited_by_count":282,"area":null},{"id":"2310.17157","title":"Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time","created":"2023-10-26","cited_by_count":252,"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":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211,"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":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2111.00064","title":"Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction","created":"2021-10-29","cited_by_count":138,"area":null},{"id":"2101.06983","title":"Scaling Deep Contrastive Learning Batch Size under Memory Limited Setup","created":"2021-01-18","cited_by_count":127,"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":"2312.06648","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","created":"2023-12-11","cited_by_count":88,"area":null},{"id":"2101.00408","title":"End-to-End Training of Neural Retrievers for Open-Domain Question Answering","created":"2021-01-02","cited_by_count":75,"area":null},{"id":"2110.00685","title":"Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classification","created":"2021-10-01","cited_by_count":67,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2205.09073","title":"Dialog Inpainting: Turning Documents into Dialogs","created":"2022-05-18","cited_by_count":56,"area":null},{"id":"2107.13602","title":"Domain-matched Pre-training Tasks for Dense Retrieval","created":"2021-07-28","cited_by_count":53,"area":null},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50,"area":null},{"id":"2112.07708","title":"Learning to Retrieve Passages without Supervision","created":"2021-12-14","cited_by_count":46,"area":null},{"id":"2306.15222","title":"Learning to Rank in Generative Retrieval","created":"2023-06-27","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":"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":"2106.02902","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","created":"2021-06-05","cited_by_count":40,"area":null},{"id":"2310.05351","title":"Generalized Neural Collapse for a Large Number of Classes","created":"2023-10-09","cited_by_count":39,"area":null},{"id":"2111.06685","title":"DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documents","created":"2021-11-12","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":"2208.07652","title":"CorpusBrain: Pre-train a Generative Retrieval Model for Knowledge-Intensive Language Tasks","created":"2022-08-16","cited_by_count":36,"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":"2403.13310","title":"A Semantic Search Engine for Mathlib4","created":"2024-03-20","cited_by_count":31,"area":null},{"id":"2106.12657","title":"Extreme Multi-label Learning for Semantic Matching in Product Search","created":"2021-06-23","cited_by_count":28,"area":null},{"id":"2212.10380","title":"What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary","created":"2022-12-20","cited_by_count":28,"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":"2105.01736","title":"Retrieving Complex Tables with Multi-Granular Graph Representation Learning","created":"2021-05-04","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":"2306.00424","title":"End-to-end Knowledge Retrieval with Multi-modal Queries","created":"2023-06-01","cited_by_count":23,"area":null},{"id":"2201.07745","title":"Improving Biomedical Information Retrieval with Neural Retrievers","created":"2022-01-19","cited_by_count":20,"area":null},{"id":"2306.02003","title":"On Optimal Caching and Model Multiplexing for Large Model Inference","created":"2023-06-03","cited_by_count":20,"area":null},{"id":"2105.13003","title":"Rethinking InfoNCE: How Many Negative Samples Do You Need?","created":"2021-05-27","cited_by_count":19,"area":null},{"id":"2102.09268","title":"Training Large-Scale News Recommenders with Pretrained Language Models in the Loop","created":"2021-02-18","cited_by_count":18,"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":"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":"2208.07670","title":"ConTextual Masked Auto-Encoder for Dense Passage Retrieval","created":"2022-08-16","cited_by_count":16,"area":null},{"id":"2211.05165","title":"Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database","created":"2022-11-09","cited_by_count":16,"area":null},{"id":"2305.16675","title":"Multiview Identifiers Enhanced Generative Retrieval","created":"2023-05-26","cited_by_count":16,"area":null},{"id":"2112.08652","title":"Extreme Zero-Shot Learning for Extreme Text Classification","created":"2021-12-16","cited_by_count":15,"area":null},{"id":"2203.06942","title":"Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering","created":"2022-03-14","cited_by_count":15,"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":"2301.13779","title":"FLAME: A small language model for spreadsheet formulas","created":"2023-01-31","cited_by_count":15,"area":null},{"id":"2312.10661","title":"Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-hoc Retrieval","created":"2023-12-17","cited_by_count":15,"area":null},{"id":"2103.04037","title":"Perspectives and Prospects on Transformer Architecture for Cross-Modal Tasks with Language and Vision","created":"2021-03-06","cited_by_count":14,"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":"2210.08410","title":"ELIAS: End-to-End Learning to Index and Search in Large Output Spaces","created":"2022-10-16","cited_by_count":14,"area":null},{"id":"2101.10726","title":"Regulatory Compliance through Doc2Doc Information Retrieval: A case study in EU/UK legislation where text similarity has limitations","created":"2021-01-26","cited_by_count":13,"area":null},{"id":"2102.13247","title":"DOCENT: Learning Self-Supervised Entity Representations from Large Document Collections","created":"2021-02-26","cited_by_count":13,"area":null},{"id":"2110.07731","title":"CCQA: A New Web-Scale Question Answering Dataset for Model Pre-Training","created":"2021-10-14","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":"2211.00640","title":"CascadeXML: Rethinking Transformers for End-to-end Multi-resolution Training in Extreme Multi-label Classification","created":"2022-10-29","cited_by_count":12,"area":null},{"id":"2302.03505","title":"OPORP: One Permutation + One Random Projection","created":"2023-02-07","cited_by_count":12,"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":"2306.16478","title":"Pre-Training Multi-Modal Dense Retrievers for Outside-Knowledge Visual Question Answering","created":"2023-06-28","cited_by_count":10,"area":null},{"id":"2104.07800","title":"Towards Robust Neural Retrieval Models with Synthetic Pre-Training","created":"2021-04-15","cited_by_count":9,"area":null},{"id":"2105.02978","title":"Graph-based Multilingual Product Retrieval in E-commerce Search","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2205.10455","title":"Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection","created":"2022-05-20","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":"2402.01173","title":"Efficient Prompt Caching via Embedding Similarity","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2407.10691","title":"$\\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2103.01495","title":"Task-Adaptive Neural Network Search with Meta-Contrastive Learning","created":"2021-03-02","cited_by_count":8,"area":null},{"id":"2307.15893","title":"Online Matching: A Real-time Bandit System for Large-scale Recommendations","created":"2023-07-29","cited_by_count":8,"area":null},{"id":"2104.08443","title":"A Graph-guided Multi-round Retrieval Method for Conversational Open-domain Question Answering","created":"2021-04-17","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":"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":"2305.12349","title":"PINA: Leveraging Side Information in eXtreme Multi-label Classification via Predicted Instance Neighborhood Aggregation","created":"2023-05-21","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":"2406.07640","title":"When is an Embedding Model More Promising than Another?","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2106.00590","title":"NewsEmbed: Modeling News through Pre-trained Document Representations","created":"2021-06-01","cited_by_count":6,"area":null},{"id":"2201.11115","title":"CsFEVER and CTKFacts: Acquiring Czech data for fact verification","created":"2022-01-26","cited_by_count":6,"area":null},{"id":"2201.02026","title":"Fortunately, Discourse Markers Can Enhance Language Models for Sentiment Analysis","created":"2022-01-06","cited_by_count":5,"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":"2212.07699","title":"Retrieval-based Disentangled Representation Learning with Natural Language Supervision","created":"2022-12-15","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":"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":"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":"2105.12682","title":"Zero-shot Medical Entity Retrieval without Annotation: Learning From Rich Knowledge Graph Semantics","created":"2021-05-26","cited_by_count":4,"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":"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":"2305.14963","title":"PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification","created":"2023-05-24","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":"2405.07615","title":"ViWikiFC: Fact-Checking for Vietnamese Wikipedia-Based Textual Knowledge Source","created":"2024-05-13","cited_by_count":4,"area":null},{"id":"2509.16411","title":"Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2110.00159","title":"Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning","created":"2021-10-01","cited_by_count":3,"area":null}],"next_cursor":"100"}