{"total":136,"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":"2503.09516","title":"Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning","created":"2025-03-12","cited_by_count":1444,"area":"lr"},{"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":"2412.16855","title":"GME: Improving Universal Multimodal Retrieval by Multimodal LLMs","created":"2024-12-22","cited_by_count":170,"area":"mllm"},{"id":"2503.19470","title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","created":"2025-03-25","cited_by_count":161,"area":"lr"},{"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":"2410.05983","title":"Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG","created":"2024-10-08","cited_by_count":123,"area":"rag"},{"id":"2404.10981","title":"A Survey on Retrieval-Augmented Text Generation for Large Language Models","created":"2024-04-17","cited_by_count":77,"area":"rag"},{"id":"2403.03187","title":"Reliable, Adaptable, and Attributable Language Models with Retrieval","created":"2024-03-05","cited_by_count":73,"area":"rag"},{"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":"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":"2502.06872","title":"Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A Survey","created":"2025-02-08","cited_by_count":30,"area":"rag"},{"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":"2402.17497","title":"REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering","created":"2024-02-27","cited_by_count":28,"area":"rag"},{"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":"2402.17505","title":"BASES: Large-scale Web Search User Simulation with Large Language Model based Agents","created":"2024-02-27","cited_by_count":25,"area":"agents"},{"id":"2305.15053","title":"Decomposing Complex Queries for Tip-of-the-tongue Retrieval","created":"2023-05-24","cited_by_count":24,"area":null},{"id":"2504.05731","title":"Retrieval Augmented Generation with Collaborative Filtering for Personalized Text Generation","created":"2025-04-08","cited_by_count":24,"area":"rag"},{"id":"2504.08758","title":"Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generation","created":"2025-03-30","cited_by_count":23,"area":"rag"},{"id":"2305.17653","title":"Prompt-Guided Retrieval Augmentation for Non-Knowledge-Intensive Tasks","created":"2023-05-28","cited_by_count":21,"area":"rag"},{"id":"2406.05087","title":"Corpus Poisoning via Approximate Greedy Gradient Descent","created":"2024-06-07","cited_by_count":21,"area":"rag"},{"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":"2501.13742","title":"An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities","created":"2025-01-23","cited_by_count":18,"area":"rag"},{"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":"2502.07555","title":"O1 Embedder: Let Retrievers Think Before Action","created":"2025-02-11","cited_by_count":15,"area":"lr"},{"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":"2408.11875","title":"Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering","created":"2024-08-20","cited_by_count":14,"area":"rag"},{"id":"2409.17275","title":"On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains","created":"2024-09-12","cited_by_count":14,"area":"rag"},{"id":"2212.10786","title":"Multi-hop Evidence Retrieval for Cross-document Relation Extraction","created":"2022-12-21","cited_by_count":13,"area":null},{"id":"2402.11035","title":"Dense Passage Retrieval: Is it Retrieving?","created":"2024-02-16","cited_by_count":12,"area":"rag"},{"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":"2512.20789","title":"X-GridAgent: An LLM-Powered Agentic AI System for Assisting Power Grid Analysis","created":"2025-12-23","cited_by_count":10,"area":"agents"},{"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":"2410.07589","title":"No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users","created":"2024-10-10","cited_by_count":9,"area":"rag"},{"id":"2410.24200","title":"Length-Induced Embedding Collapse in PLM-based Models","created":"2024-10-31","cited_by_count":9,"area":null},{"id":"2501.15067","title":"CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs","created":"2025-01-25","cited_by_count":8,"area":"rag"},{"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":"2401.17645","title":"ReSLLM: Large Language Models are Strong Resource Selectors for Federated Search","created":"2024-01-31","cited_by_count":7,"area":"rag"},{"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":"2502.03699","title":"LLM Alignment as Retriever Optimization: An Information Retrieval Perspective","created":"2025-02-06","cited_by_count":7,"area":"alignment"},{"id":"2311.02834","title":"CAME: Competitively Learning a Mixture-of-Experts Model for First-stage Retrieval","created":"2023-11-06","cited_by_count":6,"area":"moe"},{"id":"2411.12235","title":"BoolQuestions: Does Dense Retrieval Understand Boolean Logic in Language?","created":"2024-11-19","cited_by_count":6,"area":null},{"id":"2510.13272","title":"Beyond Correctness: Rewarding Faithful Reasoning in Retrieval-Augmented Generation","created":"2025-10-15","cited_by_count":6,"area":"lr"},{"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":"2409.02343","title":"NUDGE: Lightweight Non-Parametric Fine-Tuning of Embeddings for Retrieval","created":"2024-09-04","cited_by_count":5,"area":"rag"},{"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":"2505.19189","title":"POQD: Performance-Oriented Query Decomposer for Multi-vector retrieval","created":"2025-05-25","cited_by_count":5,"area":"rag"},{"id":"2508.03644","title":"Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?","created":"2025-08-05","cited_by_count":5,"area":"mllm"},{"id":"2508.17858","title":"LexSemBridge: Fine-Grained Dense Representation Enhancement through Token-Aware Embedding Augmentation","created":"2025-08-25","cited_by_count":5,"area":"rag"},{"id":"2511.01386","title":"RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets","created":"2025-11-03","cited_by_count":5,"area":"rag"},{"id":"2511.07581","title":"Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models","created":"2025-11-10","cited_by_count":5,"area":"lr"},{"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":"2606.20280","title":"ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval","created":"2026-06-18","cited_by_count":5,"area":"mllm"},{"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":"2505.14680","title":"NExT-Search: Rebuilding User Feedback Ecosystem for Generative AI Search","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2505.21471","title":"Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration","created":"2025-05-27","cited_by_count":4,"area":"agents"},{"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":"2508.01290","title":"Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities","created":"2025-08-02","cited_by_count":4,"area":"rag"},{"id":"2508.06056","title":"RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation","created":"2025-08-08","cited_by_count":4,"area":"rag"},{"id":"2509.06444","title":"HyFedRAG: A Federated Retrieval-Augmented Generation Framework for Heterogeneous and Privacy-Sensitive Data","created":"2025-09-08","cited_by_count":4,"area":"rag"},{"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":"2402.14318","title":"Assessing generalization capability of text ranking models in Polish","created":"2024-02-22","cited_by_count":3,"area":"rag"},{"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":"2411.07021","title":"Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation","created":"2024-11-11","cited_by_count":3,"area":"rag"},{"id":"2501.07766","title":"Large Language Models for Knowledge Graph Embedding: A Survey","created":"2025-01-14","cited_by_count":3,"area":null},{"id":"2508.07690","title":"LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval","created":"2025-08-11","cited_by_count":3,"area":"agents"},{"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":"2406.13249","title":"R^2AG: Incorporating Retrieval Information into Retrieval Augmented Generation","created":"2024-06-19","cited_by_count":2,"area":"rag"},{"id":"2408.05330","title":"Neural Machine Unranking","created":"2024-08-09","cited_by_count":2,"area":"safety"},{"id":"2409.13707","title":"Retrieval Augmented Generation-Based Incident Resolution Recommendation System for IT Support","created":"2024-09-06","cited_by_count":2,"area":"rag"}],"next_cursor":"100"}