{"total":79,"rows":[{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576,"area":null},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601,"area":null},{"id":"2506.05176","title":"Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models","created":"2025-06-05","cited_by_count":1261,"area":null},{"id":"2309.01219","title":"Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models","created":"2023-09-03","cited_by_count":698,"area":null},{"id":"2308.07107","title":"Large Language Models for Information Retrieval: A Survey","created":"2023-08-14","cited_by_count":331,"area":null},{"id":"2407.19669","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","created":"2024-07-29","cited_by_count":236,"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":"2407.00128","title":"When Search Engine Services meet Large Language Models: Visions and Challenges","created":"2024-06-28","cited_by_count":59,"area":null},{"id":"2309.13345","title":"BAMBOO: A Comprehensive Benchmark for Evaluating Long Text Modeling Capacities of Large Language Models","created":"2023-09-23","cited_by_count":53,"area":null},{"id":"2310.20501","title":"Neural Retrievers are Biased Towards LLM-Generated Content","created":"2023-10-31","cited_by_count":38,"area":null},{"id":"2308.09861","title":"Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method","created":"2023-08-19","cited_by_count":29,"area":null},{"id":"2305.09612","title":"Large Language Models are Built-in Autoregressive Search Engines","created":"2023-05-16","cited_by_count":27,"area":null},{"id":"2405.16089","title":"Towards Completeness-Oriented Tool Retrieval for Large Language Models","created":"2024-05-25","cited_by_count":26,"area":null},{"id":"2305.15053","title":"Decomposing Complex Queries for Tip-of-the-tongue Retrieval","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2309.04175","title":"Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese","created":"2023-09-08","cited_by_count":18,"area":null},{"id":"2310.01880","title":"AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval","created":"2023-10-03","cited_by_count":18,"area":null},{"id":"2405.16546","title":"Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration","created":"2024-05-26","cited_by_count":17,"area":null},{"id":"2406.17465","title":"Enhancing Tool Retrieval with Iterative Feedback from Large Language Models","created":"2024-06-25","cited_by_count":17,"area":null},{"id":"2407.01505","title":"Self-Cognition in Large Language Models: An Exploratory Study","created":"2024-07-01","cited_by_count":15,"area":null},{"id":"2407.06992","title":"Robust Neural Information Retrieval: An Adversarial and Out-of-distribution Perspective","created":"2024-07-09","cited_by_count":15,"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":"2212.10786","title":"Multi-hop Evidence Retrieval for Cross-document Relation Extraction","created":"2022-12-21","cited_by_count":13,"area":null},{"id":"2310.08232","title":"Language Models are Universal Embedders","created":"2023-10-12","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":"2410.01727","title":"Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing","created":"2024-10-02","cited_by_count":11,"area":null},{"id":"2402.16767","title":"CorpusBrain++: A Continual Generative Pre-Training Framework for Knowledge-Intensive Language Tasks","created":"2024-02-26","cited_by_count":10,"area":null},{"id":"2503.05150","title":"Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational History","created":"2025-03-07","cited_by_count":10,"area":null},{"id":"2402.12784","title":"Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systems","created":"2024-02-20","cited_by_count":9,"area":null},{"id":"2410.24200","title":"Length-Induced Embedding Collapse in PLM-based Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2502.12598","title":"Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion","created":"2025-02-18","cited_by_count":8,"area":null},{"id":"2509.10697","title":"A Survey on Retrieval And Structuring Augmented Generation with Large Language Models","created":"2025-09-12","cited_by_count":8,"area":null},{"id":"2305.10998","title":"The Web Can Be Your Oyster for Improving Large Language Models","created":"2023-05-18","cited_by_count":7,"area":null},{"id":"2309.09403","title":"Selecting which Dense Retriever to use for Zero-Shot Search","created":"2023-09-18","cited_by_count":7,"area":null},{"id":"2402.10666","title":"MURRE: Multi-Hop Table Retrieval with Removal for Open-Domain Text-to-SQL","created":"2024-02-16","cited_by_count":7,"area":null},{"id":"2404.08535","title":"Generalized Contrastive Learning for Multi-Modal Retrieval and Ranking","created":"2024-04-12","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":"2411.12235","title":"BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?","created":"2024-11-19","cited_by_count":6,"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":"2308.08378","title":"Advancing continual lifelong learning in neural information retrieval: definition, dataset, framework, and empirical evaluation","created":"2023-08-16","cited_by_count":5,"area":null},{"id":"2410.20163","title":"UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers","created":"2024-10-26","cited_by_count":5,"area":null},{"id":"2412.07462","title":"Bilingual BSARD: Extending Statutory Article Retrieval to Dutch","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2502.12361","title":"ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining","created":"2025-02-17","cited_by_count":5,"area":null},{"id":"2503.08684","title":"Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2511.22150","title":"From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2312.10171","title":"Pipeline and Dataset Generation for Automated Fact-checking in Almost Any Language","created":"2023-12-15","cited_by_count":4,"area":null},{"id":"2504.03169","title":"REJEPA: A Novel Joint-Embedding Predictive Architecture for Efficient Remote Sensing Image Retrieval","created":"2025-04-04","cited_by_count":4,"area":null},{"id":"2506.16444","title":"REIS: A High-Performance and Energy-Efficient Retrieval System with In-Storage Processing","created":"2025-06-19","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":"2212.08841","title":"AugTriever: Unsupervised Dense Retrieval and Domain Adaptation by Scalable Data Augmentation","created":"2022-12-17","cited_by_count":3,"area":null},{"id":"2311.13921","title":"Some Like It Small: Czech Semantic Embedding Models for Industry Applications","created":"2023-11-23","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":"2501.07766","title":"Large Language Models for Knowledge Graph Embedding: A Survey","created":"2025-01-14","cited_by_count":3,"area":null},{"id":"2512.10999","title":"KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering","created":"2025-12-10","cited_by_count":3,"area":null},{"id":"2310.01217","title":"ScaLearn: Simple and Highly Parameter-Efficient Task Transfer by Learning to Scale","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2404.00211","title":"Multi-Conditional Ranking with Large Language Models","created":"2024-03-30","cited_by_count":2,"area":null},{"id":"2405.20994","title":"CWRCzech: 100M Query-Document Czech Click Dataset and Its Application to Web Relevance Ranking","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2503.01334","title":"Composed Multi-modal Retrieval: A Survey of Approaches and Applications","created":"2025-03-03","cited_by_count":2,"area":null},{"id":"2505.07166","title":"Pre-training vs. Fine-tuning: A Reproducibility Study on Dense Retrieval Knowledge Acquisition","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2310.07560","title":"ROMO: Retrieval-enhanced Offline Model-based Optimization","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2402.12997","title":"Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism","created":"2024-02-20","cited_by_count":1,"area":null},{"id":"2501.17338","title":"Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection","created":"2025-01-28","cited_by_count":1,"area":null},{"id":"2402.02932","title":"Domain Adaptation of Multilingual Semantic Search -- Literature Review","created":"2024-02-05","cited_by_count":0,"area":null},{"id":"2403.18671","title":"Fact Checking Beyond Training Set","created":"2024-03-27","cited_by_count":0,"area":null},{"id":"2409.16497","title":"Unsupervised Text Representation Learning via Instruction-Tuning for Zero-Shot Dense Retrieval","created":"2024-09-24","cited_by_count":0,"area":null},{"id":"2410.20315","title":"Deep Learning Based Dense Retrieval: A Comparative Study","created":"2024-10-27","cited_by_count":0,"area":null},{"id":"2506.04762","title":"GOLFer: Smaller LM-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrieval","created":"2025-06-05","cited_by_count":0,"area":null},{"id":"2507.20718","title":"Uncertainty-driven Embedding Convolution","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2508.11670","title":"RRRA: Resampling and Reranking through a Retriever Adapter","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2508.11784","title":"Ontology-Guided Query Expansion for Biomedical Document Retrieval using Large Language Models","created":"2025-08-15","cited_by_count":0,"area":null},{"id":"2508.20778","title":"SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.17766","title":"A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.08774","title":"Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2601.09723","title":"SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novels","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2606.17664","title":"Temporal Preference Optimization for Unsupervised Retrieval","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2606.25237","title":"Extreme Meta-Classification for Large-Scale Zero-Shot Retrieval","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2606.25674","title":"BitNet Text Embeddings","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.13920","title":"DeepStress: Stress-Testing Deep Search Agents","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.24793","title":"Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.18610","title":"Denoising-Aware Inversion: Revealing Privacy Risks in Noise-Protected Text Embeddings","created":"2026-08-19","cited_by_count":0,"area":null}],"next_cursor":null}