{"total":122,"rows":[{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173,"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":"2108.11601","title":"Retrieval Augmented Code Generation and Summarization","created":"2021-08-26","cited_by_count":149,"area":"rag"},{"id":"2307.13565","title":"Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities","created":"2023-07-25","cited_by_count":130,"area":null},{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2402.13598","title":"User-LLM: Efficient LLM Contextualization with User Embeddings","created":"2024-02-21","cited_by_count":76,"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":"2108.13454","title":"Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback","created":"2021-08-30","cited_by_count":47,"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":"2107.11976","title":"One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval","created":"2021-07-26","cited_by_count":46,"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":"2502.01113","title":"GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation","created":"2025-02-03","cited_by_count":40,"area":"rag"},{"id":"2104.06245","title":"Understanding Hard Negatives in Noise Contrastive Estimation","created":"2021-04-13","cited_by_count":39,"area":null},{"id":"2404.18443","title":"BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers","created":"2024-04-29","cited_by_count":38,"area":null},{"id":"2412.08802","title":"jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images","created":"2024-12-11","cited_by_count":37,"area":null},{"id":"2104.05763","title":"Few-shot Intent Classification and Slot Filling with Retrieved Examples","created":"2021-04-12","cited_by_count":35,"area":null},{"id":"2110.02369","title":"EntQA: Entity Linking as Question Answering","created":"2021-10-05","cited_by_count":34,"area":null},{"id":"2112.07887","title":"Knowledge-Rich Self-Supervision for Biomedical Entity Linking","created":"2021-12-15","cited_by_count":31,"area":null},{"id":"2305.10703","title":"ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval","created":"2023-05-18","cited_by_count":26,"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":"2208.14565","title":"Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning","created":"2022-08-30","cited_by_count":24,"area":null},{"id":"2303.07616","title":"The Life Cycle of Knowledge in Big Language Models: A Survey","created":"2023-03-14","cited_by_count":23,"area":null},{"id":"2109.01242","title":"Entity Linking and Discovery via Arborescence-based Supervised Clustering","created":"2021-09-02","cited_by_count":22,"area":null},{"id":"2109.12520","title":"Entity Linking Meets Deep Learning: Techniques and Solutions","created":"2021-09-26","cited_by_count":22,"area":null},{"id":"2406.05087","title":"Corpus Poisoning via Approximate Greedy Gradient Descent","created":"2024-06-07","cited_by_count":21,"area":"rag"},{"id":"2202.06212","title":"Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search","created":"2022-02-13","cited_by_count":17,"area":"distill"},{"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":"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":"2103.05028","title":"Fast and Effective Biomedical Entity Linking Using a Dual Encoder","created":"2021-03-08","cited_by_count":16,"area":null},{"id":"2110.05362","title":"Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference","created":"2021-10-11","cited_by_count":16,"area":null},{"id":"2110.15705","title":"Distilling Relation Embeddings from Pre-trained Language Models","created":"2021-09-21","cited_by_count":15,"area":null},{"id":"2402.17238","title":"Does Negative Sampling Matter? A Review with Insights into its Theory and Applications","created":"2024-02-27","cited_by_count":15,"area":null},{"id":"2101.02394","title":"Read, Retrospect, Select: An MRC Framework to Short Text Entity Linking","created":"2021-01-07","cited_by_count":14,"area":null},{"id":"2109.02237","title":"BERT might be Overkill: A Tiny but Effective Biomedical Entity Linker based on Residual Convolutional Neural Networks","created":"2021-09-06","cited_by_count":14,"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":"2108.08468","title":"QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction","created":"2021-08-19","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":"2105.12932","title":"Contrastive Fine-tuning Improves Robustness for Neural Rankers","created":"2021-05-27","cited_by_count":12,"area":null},{"id":"2106.09795","title":"LNN-EL: A Neuro-Symbolic Approach to Short-text Entity Linking","created":"2021-06-17","cited_by_count":11,"area":null},{"id":"2305.07402","title":"Synergistic Interplay between Search and Large Language Models for Information Retrieval","created":"2023-05-12","cited_by_count":11,"area":null},{"id":"2310.14684","title":"SpEL: Structured Prediction for Entity Linking","created":"2023-10-23","cited_by_count":11,"area":null},{"id":"2106.07352","title":"MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network","created":"2021-06-02","cited_by_count":10,"area":null},{"id":"2202.13404","title":"Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity Linking","created":"2022-02-27","cited_by_count":10,"area":null},{"id":"2301.11489","title":"Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation","created":"2023-01-27","cited_by_count":10,"area":"synth"},{"id":"2305.05973","title":"Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2406.12329","title":"Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport","created":"2024-06-18","cited_by_count":10,"area":"safety"},{"id":"2104.03986","title":"Deep Indexed Active Learning for Matching Heterogeneous Entity Representations","created":"2021-04-08","cited_by_count":9,"area":null},{"id":"2109.05716","title":"MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations","created":"2021-09-13","cited_by_count":9,"area":null},{"id":"2210.02771","title":"Modelling Commonsense Properties using Pre-Trained Bi-Encoders","created":"2022-10-06","cited_by_count":9,"area":null},{"id":"2204.08173","title":"TABi: Type-Aware Bi-Encoders for Open-Domain Entity Retrieval","created":"2022-04-18","cited_by_count":8,"area":null},{"id":"2310.05589","title":"DRIN: Dynamic Relation Interactive Network for Multimodal Entity Linking","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2411.19655","title":"Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-Oasis","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2303.06791","title":"Beyond Single Items: Exploring User Preferences in Item Sets with the Conversational Playlist Curation Dataset","created":"2023-03-13","cited_by_count":7,"area":null},{"id":"2103.04156","title":"Improving Zero-Shot Entity Retrieval through Effective Dense Representations","created":"2021-03-06","cited_by_count":6,"area":null},{"id":"2108.07931","title":"Learning Federated Representations and Recommendations with Limited Negatives","created":"2021-08-18","cited_by_count":6,"area":null},{"id":"2112.01989","title":"Survey on English Entity Linking on Wikidata","created":"2021-12-03","cited_by_count":6,"area":null},{"id":"2207.05280","title":"Effective Few-Shot Named Entity Linking by Meta-Learning","created":"2022-07-12","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":"2310.12450","title":"A Read-and-Select Framework for Zero-shot Entity Linking","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2104.07858","title":"Matching-oriented Product Quantization For Ad-hoc Retrieval","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2205.12570","title":"EDIN: An End-to-end Benchmark and Pipeline for Unknown Entity Discovery and Indexing","created":"2022-05-25","cited_by_count":5,"area":null},{"id":"2303.04426","title":"NASTyLinker: NIL-Aware Scalable Transformer-based Entity Linker","created":"2023-03-08","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":"2306.10047","title":"Neighborhood-based Hard Negative Mining for Sequential Recommendation","created":"2023-06-12","cited_by_count":5,"area":null},{"id":"2505.11683","title":"Evaluating Design Decisions for Dual Encoder-based Entity Disambiguation","created":"2025-05-16","cited_by_count":5,"area":null},{"id":"2104.02667","title":"Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations","created":"2021-04-06","cited_by_count":4,"area":null},{"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":"2310.08221","title":"SimCKP: Simple Contrastive Learning of Keyphrase Representations","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2401.05125","title":"BELHD: Improving Biomedical Entity Linking with Homonoym Disambiguation","created":"2024-01-10","cited_by_count":4,"area":null},{"id":"2401.10337","title":"Noise Contrastive Estimation-based Matching Framework for Low-Resource Security Attack Pattern Recognition","created":"2024-01-18","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":"2210.12308","title":"PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding","created":"2022-10-22","cited_by_count":3,"area":null},{"id":"2301.02458","title":"Topics as Entity Clusters: Entity-based Topics from Large Language Models and Graph Neural Networks","created":"2023-01-06","cited_by_count":3,"area":null},{"id":"2302.10454","title":"KG-ECO: Knowledge Graph Enhanced Entity Correction for Query Rewriting","created":"2023-02-21","cited_by_count":3,"area":null},{"id":"2305.14588","title":"Evaluating end-to-end entity linking on domain-specific knowledge bases: Learning about ancient technologies from museum collections","created":"2023-05-23","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":"2310.18619","title":"Dense Retrieval as Indirect Supervision for Large-space Decision Making","created":"2023-10-28","cited_by_count":3,"area":null},{"id":"2411.06151","title":"Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust","created":"2024-11-09","cited_by_count":3,"area":null},{"id":"2504.06293","title":"Generative AI Enhanced Financial Risk Management Information Retrieval","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2204.08887","title":"Cross-Lingual Phrase Retrieval","created":"2022-04-19","cited_by_count":2,"area":null},{"id":"2209.00351","title":"Find the Funding: Entity Linking with Incomplete Funding Knowledge Bases","created":"2022-09-01","cited_by_count":2,"area":null},{"id":"2210.12314","title":"A Benchmark Study of Contrastive Learning for Arabic Social Meaning","created":"2022-10-22","cited_by_count":2,"area":null},{"id":"2301.13318","title":"Proxy-based Zero-Shot Entity Linking by Effective Candidate Retrieval","created":"2023-01-30","cited_by_count":2,"area":null},{"id":"2305.19019","title":"Event-Centric Query Expansion in Web Search","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2309.10506","title":"Enhancing Open-Domain Table Question Answering via Syntax- and Structure-aware Dense Retrieval","created":"2023-09-19","cited_by_count":2,"area":null},{"id":"2403.18667","title":"Improving Content Recommendation: Knowledge Graph-Based Semantic Contrastive Learning for Diversity and Cold-Start Users","created":"2024-03-27","cited_by_count":2,"area":null},{"id":"2405.12801","title":"Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2508.03865","title":"An Entity Linking Agent for Question Answering","created":"2025-08-05","cited_by_count":2,"area":"agents"},{"id":"2101.09311","title":"Drug and Disease Interpretation Learning with Biomedical Entity Representation Transformer","created":"2021-01-22","cited_by_count":1,"area":null},{"id":"2211.06452","title":"Cross-Platform and Cross-Domain Abusive Language Detection with Supervised Contrastive Learning","created":"2022-11-11","cited_by_count":1,"area":null},{"id":"2212.08775","title":"RISE: Leveraging Retrieval Techniques for Summarization Evaluation","created":"2022-12-17","cited_by_count":1,"area":null},{"id":"2307.00342","title":"Improving Multitask Retrieval by Promoting Task Specialization","created":"2023-07-01","cited_by_count":1,"area":null},{"id":"2310.13990","title":"A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification","created":"2023-10-21","cited_by_count":1,"area":null},{"id":"2403.16820","title":"Cross-lingual Contextualized Phrase Retrieval","created":"2024-03-25","cited_by_count":1,"area":null},{"id":"2412.09370","title":"Word Sense Linking: Disambiguating Outside the Sandbox","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2507.05933","title":"Semantic Certainty Assessment in Vector Retrieval Systems: A Novel Framework for Embedding Quality Evaluation","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.15380","title":"Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios","created":"2025-09-18","cited_by_count":1,"area":null}],"next_cursor":"100"}