{"total":229,"rows":[{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173,"area":null},{"id":"2112.08633","title":"Learning To Retrieve Prompts for In-Context Learning","created":"2021-12-16","cited_by_count":648,"area":null},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463,"area":null},{"id":"2112.07899","title":"Large Dual Encoders Are Generalizable Retrievers","created":"2021-12-15","cited_by_count":456,"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":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"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":"2104.06979","title":"TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning","created":"2021-04-14","cited_by_count":116,"area":null},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89,"area":null},{"id":"2103.12011","title":"Open Domain Question Answering over Tables via Dense Retrieval","created":"2021-03-22","cited_by_count":74,"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":"2103.08784","title":"LightningDOT: Pre-training Visual-Semantic Embeddings for Real-Time Image-Text Retrieval","created":"2021-03-16","cited_by_count":44,"area":null},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40,"area":null},{"id":"2402.16829","title":"GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning","created":"2024-02-26","cited_by_count":40,"area":"rag"},{"id":"2311.11315","title":"TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Systems","created":"2023-11-19","cited_by_count":39,"area":"agents"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2204.10050","title":"SemEval-2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding","created":"2022-04-21","cited_by_count":36,"area":null},{"id":"2309.17050","title":"Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models","created":"2023-09-29","cited_by_count":35,"area":"rag"},{"id":"2211.07733","title":"Speaking Multiple Languages Affects the Moral Bias of Language Models","created":"2022-11-14","cited_by_count":34,"area":null},{"id":"2401.07883","title":"The Chronicles of RAG: The Retriever, the Chunk and the Generator","created":"2024-01-15","cited_by_count":34,"area":"rag"},{"id":"2202.13469","title":"UCTopic: Unsupervised Contrastive Learning for Phrase Representations and Topic Mining","created":"2022-02-27","cited_by_count":33,"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":"2210.09304","title":"Non-Contrastive Learning Meets Language-Image Pre-Training","created":"2022-10-17","cited_by_count":25,"area":null},{"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":"2210.05758","title":"Decoupled Context Processing for Context Augmented Language Modeling","created":"2022-10-11","cited_by_count":24,"area":null},{"id":"2102.05756","title":"Artificial intelligence in communication impacts language and social relationships","created":"2021-02-10","cited_by_count":22,"area":null},{"id":"2311.08110","title":"Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning","created":"2023-11-14","cited_by_count":21,"area":null},{"id":"2402.07440","title":"Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT","created":"2024-02-12","cited_by_count":21,"area":null},{"id":"2109.12599","title":"DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings","created":"2021-09-26","cited_by_count":19,"area":null},{"id":"2204.07120","title":"Exploring Dual Encoder Architectures for Question Answering","created":"2022-04-14","cited_by_count":19,"area":null},{"id":"2205.14912","title":"E2S2: Encoding-Enhanced Sequence-to-Sequence Pretraining for Language Understanding and Generation","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2409.02727","title":"Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?","created":"2024-09-04","cited_by_count":19,"area":null},{"id":"2210.04261","title":"Noise-Robust De-Duplication at Scale","created":"2022-10-09","cited_by_count":17,"area":null},{"id":"2307.10778","title":"Extreme Multi-Label Skill Extraction Training using Large Language Models","created":"2023-07-20","cited_by_count":17,"area":null},{"id":"2102.02096","title":"Learning to Select External Knowledge with Multi-Scale Negative Sampling","created":"2021-02-03","cited_by_count":16,"area":null},{"id":"2306.09237","title":"One Law, Many Languages: Benchmarking Multilingual Legal Reasoning for Judicial Support","created":"2023-06-15","cited_by_count":16,"area":"lr"},{"id":"2203.14655","title":"Few-Shot Learning with Siamese Networks and Label Tuning","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2212.07588","title":"DeepJoin: Joinable Table Discovery with Pre-trained Language Models","created":"2022-12-15","cited_by_count":15,"area":null},{"id":"2402.05617","title":"Deep Learning-based Computational Job Market Analysis: A Survey on Skill Extraction and Classification from Job Postings","created":"2024-02-08","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":"2403.02694","title":"MeanCache: User-Centric Semantic Caching for LLM Web Services","created":"2024-03-05","cited_by_count":14,"area":null},{"id":"2207.08349","title":"Retweet-BERT: Political Leaning Detection Using Language Features and Information Diffusion on Social Networks","created":"2022-07-18","cited_by_count":13,"area":null},{"id":"2210.06331","title":"RedHOT: A Corpus of Annotated Medical Questions, Experiences, and Claims on Social Media","created":"2022-10-12","cited_by_count":13,"area":null},{"id":"2203.14541","title":"Specialized Document Embeddings for Aspect-based Similarity of Research Papers","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2209.05972","title":"Don't Judge a Language Model by Its Last Layer: Contrastive Learning with Layer-Wise Attention Pooling","created":"2022-09-13","cited_by_count":12,"area":null},{"id":"2207.12759","title":"Training Effective Neural Sentence Encoders from Automatically Mined Paraphrases","created":"2022-07-26","cited_by_count":11,"area":null},{"id":"2401.00893","title":"Social-LLM: Modeling User Behavior at Scale using Language Models and Social Network Data","created":"2023-12-31","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":"2103.12777","title":"Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learning","created":"2021-03-23","cited_by_count":10,"area":null},{"id":"2204.08952","title":"Retrieval Enhanced Data Augmentation for Question Answering on Privacy Policies","created":"2022-04-19","cited_by_count":10,"area":null},{"id":"2504.07199","title":"SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog","created":"2025-04-09","cited_by_count":10,"area":null},{"id":"2106.02017","title":"A Dataset and Baselines for Multilingual Reply Suggestion","created":"2021-06-03","cited_by_count":9,"area":null},{"id":"2210.04447","title":"CrowdChecked: Detecting Previously Fact-Checked Claims in Social Media","created":"2022-10-10","cited_by_count":9,"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":"2306.02516","title":"SamToNe: Improving Contrastive Loss for Dual Encoder Retrieval Models with Same Tower Negatives","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2503.15191","title":"Optimizing Retrieval Strategies for Financial Question Answering Documents in Retrieval-Augmented Generation Systems","created":"2025-03-19","cited_by_count":9,"area":"rag"},{"id":"2505.21439","title":"Towards Better Instruction Following Retrieval Models","created":"2025-05-27","cited_by_count":9,"area":null},{"id":"2402.13043","title":"Effective and Efficient Conversation Retrieval for Dialogue State Tracking with Implicit Text Summaries","created":"2024-02-20","cited_by_count":8,"area":null},{"id":"2110.03949","title":"CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learning","created":"2021-10-08","cited_by_count":7,"area":null},{"id":"2207.10802","title":"Combing for Credentials: Active Pattern Extraction from Smart Reply","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2307.16638","title":"VacancySBERT: the approach for representation of titles and skills for semantic similarity search in the recruitment domain","created":"2023-07-31","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":"2407.21139","title":"Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning","created":"2024-07-30","cited_by_count":7,"area":null},{"id":"2510.19791","title":"ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers","created":"2025-10-22","cited_by_count":7,"area":"lr"},{"id":"2108.07931","title":"Learning Federated Representations and Recommendations with Limited Negatives","created":"2021-08-18","cited_by_count":6,"area":null},{"id":"2212.10528","title":"HYRR: Hybrid Infused Reranking for Passage Retrieval","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2308.00762","title":"Self-Supervised Contrastive BERT Fine-tuning for Fusion-based Reviewed-Item Retrieval","created":"2023-08-01","cited_by_count":6,"area":null},{"id":"2311.01230","title":"Multi-Operational Mathematical Derivations in Latent Space","created":"2023-11-02","cited_by_count":6,"area":null},{"id":"2410.14043","title":"Retrieval of Temporal Event Sequences from Textual Descriptions","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2505.12950","title":"GuRE:Generative Query REwriter for Legal Passage Retrieval","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2103.17205","title":"Augmenting Poetry Composition with Verse by Verse","created":"2021-03-31","cited_by_count":5,"area":null},{"id":"2112.09628","title":"Sparsifying Sparse Representations for Passage Retrieval by Top-$k$ Masking","created":"2021-12-17","cited_by_count":5,"area":null},{"id":"2206.09600","title":"SPBERTQA: A Two-Stage Question Answering System Based on Sentence Transformers for Medical Texts","created":"2022-06-20","cited_by_count":5,"area":null},{"id":"2208.11194","title":"Bitext Mining for Low-Resource Languages via Contrastive Learning","created":"2022-08-23","cited_by_count":5,"area":null},{"id":"2210.06470","title":"Who Wrote this? How Smart Replies Impact Language and Agency in the Workplace","created":"2022-10-07","cited_by_count":5,"area":null},{"id":"2210.09773","title":"Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation","created":"2022-10-18","cited_by_count":5,"area":null},{"id":"2211.04205","title":"Preserving Semantics in Textual Adversarial Attacks","created":"2022-11-08","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":"2304.01003","title":"QUADRo: Dataset and Models for QUestion-Answer Database Retrieval","created":"2023-03-30","cited_by_count":5,"area":null},{"id":"2306.06228","title":"AVScan2Vec: Feature Learning on Antivirus Scan Data for Production-Scale Malware Corpora","created":"2023-06-09","cited_by_count":5,"area":null},{"id":"2307.07851","title":"AspectCSE: Sentence Embeddings for Aspect-based Semantic Textual Similarity Using Contrastive Learning and Structured Knowledge","created":"2023-07-15","cited_by_count":5,"area":null},{"id":"2407.17760","title":"TwIPS: A Large Language Model Powered Texting Application to Simplify Conversational Nuances for Autistic Users","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2409.02343","title":"NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval","created":"2024-09-04","cited_by_count":5,"area":"rag"},{"id":"2412.07462","title":"Bilingual BSARD: Extending Statutory Article Retrieval to Dutch","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2103.16429","title":"Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention","created":"2021-03-30","cited_by_count":4,"area":null},{"id":"2204.10543","title":"Zero and Few-shot Learning for Author Profiling","created":"2022-04-22","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":"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":"2402.11489","title":"What's the Plan? Evaluating and Developing Planning-Aware Techniques for Language Models","created":"2024-02-18","cited_by_count":4,"area":null},{"id":"2407.19527","title":"Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family","created":"2024-07-28","cited_by_count":4,"area":null},{"id":"2409.19680","title":"Instruction Embedding: Latent Representations of Instructions Towards Task Identification","created":"2024-09-29","cited_by_count":4,"area":null},{"id":"2410.05006","title":"SkillMatch: Evaluating Self-supervised Learning of Skill Relatedness","created":"2024-10-07","cited_by_count":4,"area":null},{"id":"2410.20056","title":"Multi-Field Adaptive Retrieval","created":"2024-10-26","cited_by_count":4,"area":"rag"},{"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":"2503.03360","title":"Transformers for molecular property prediction: Domain adaptation efficiently improves performance","created":"2025-03-05","cited_by_count":4,"area":null},{"id":"2510.22264","title":"PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embedding","created":"2025-10-25","cited_by_count":4,"area":null},{"id":"2110.02030","title":"Exploiting Twitter as Source of Large Corpora of Weakly Similar Pairs for Semantic Sentence Embeddings","created":"2021-10-05","cited_by_count":3,"area":null},{"id":"2205.06733","title":"Arithmetic-Based Pretraining -- Improving Numeracy of Pretrained Language Models","created":"2022-05-13","cited_by_count":3,"area":null},{"id":"2210.12308","title":"PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding","created":"2022-10-22","cited_by_count":3,"area":null}],"next_cursor":"100"}