{"total":88,"rows":[{"id":"2502.14802","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","created":"2025-02-20","cited_by_count":231,"area":"rag"},{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104,"area":null},{"id":"2502.18418","title":"Rank1: Test-Time Compute for Reranking in Information Retrieval","created":"2025-02-25","cited_by_count":70,"area":"lr"},{"id":"2503.01763","title":"Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models","created":"2025-03-03","cited_by_count":47,"area":"agents"},{"id":"2409.11136","title":"Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models","created":"2024-09-17","cited_by_count":40,"area":null},{"id":"2412.09563","title":"Does Representation Matter? Exploring Intermediate Layers in Large Language Models","created":"2024-12-12","cited_by_count":34,"area":null},{"id":"2601.08620","title":"ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarios","created":"2026-01-13","cited_by_count":26,"area":"rag"},{"id":"2408.16672","title":"Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever","created":"2024-08-29","cited_by_count":25,"area":null},{"id":"2505.23794","title":"R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning","created":"2025-05-26","cited_by_count":20,"area":"lr"},{"id":"2410.10293","title":"FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG","created":"2024-10-14","cited_by_count":18,"area":"rag"},{"id":"2508.13250","title":"Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information","created":"2025-08-18","cited_by_count":17,"area":"lr"},{"id":"2510.03204","title":"FocusAgent: Simple Yet Effective Ways of Trimming the Large Context of Web Agents","created":"2025-10-03","cited_by_count":16,"area":"agents"},{"id":"2502.20995","title":"The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems","created":"2025-02-28","cited_by_count":14,"area":"rag"},{"id":"2503.04554","title":"Compositional Translation: A Novel LLM-based Approach for Low-resource Machine Translation","created":"2025-03-06","cited_by_count":14,"area":null},{"id":"2410.03435","title":"A General Framework for Producing Interpretable Semantic Text Embeddings","created":"2024-10-04","cited_by_count":10,"area":null},{"id":"2505.07546","title":"GRADA: Graph-based Reranking against Adversarial Documents Attack","created":"2025-05-12","cited_by_count":10,"area":"rag"},{"id":"2507.03674","title":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking","created":"2025-07-04","cited_by_count":8,"area":"agents"},{"id":"2502.17163","title":"MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation","created":"2025-02-24","cited_by_count":7,"area":"rag"},{"id":"2509.01324","title":"KoBLEX: Open Legal Question Answering with Multi-hop Reasoning","created":"2025-09-01","cited_by_count":7,"area":"lr"},{"id":"2509.25189","title":"InfoAgent: Advancing Autonomous Information-Seeking Agents","created":"2025-09-29","cited_by_count":7,"area":"agents"},{"id":"2510.07233","title":"LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding","created":"2025-10-08","cited_by_count":7,"area":"rag"},{"id":"2510.19791","title":"ToolDreamer: Instilling LLM Reasoning Into Tool Retrievers","created":"2025-10-22","cited_by_count":7,"area":"lr"},{"id":"2606.06880","title":"Towards Retrieving Interaction Spaces for Agentic Search","created":"2026-06-05","cited_by_count":7,"area":"agents"},{"id":"2505.12950","title":"GuRE:Generative Query REwriter for Legal Passage Retrieval","created":"2025-05-19","cited_by_count":6,"area":null},{"id":"2503.15573","title":"Task-Specific Data Selection for Instruction Tuning via Monosemantic Neuronal Activations","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2505.15179","title":"RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry","created":"2025-05-21","cited_by_count":5,"area":"rag"},{"id":"2507.18515","title":"A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat","created":"2025-07-24","cited_by_count":5,"area":"rag"},{"id":"2509.12042","title":"FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval","created":"2025-09-15","cited_by_count":5,"area":"rag"},{"id":"2510.04373","title":"JEF-Hinter: Leveraging Offline Knowledge for Improving Web Agents Adaptation","created":"2025-10-05","cited_by_count":5,"area":"agents"},{"id":"2410.20056","title":"Multi-Field Adaptive Retrieval","created":"2024-10-26","cited_by_count":4,"area":"rag"},{"id":"2505.08450","title":"IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation","created":"2025-05-13","cited_by_count":4,"area":"rag"},{"id":"2510.11919","title":"LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens","created":"2025-10-13","cited_by_count":4,"area":"lr"},{"id":"2410.09019","title":"MedMobile: A mobile-sized language model with clinical capabilities","created":"2024-10-11","cited_by_count":3,"area":"lr"},{"id":"2510.05310","title":"RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts","created":"2025-10-06","cited_by_count":3,"area":"safety"},{"id":"2502.08557","title":"A New Query Expansion Approach via Agent-Mediated Dialogic Inquiry","created":"2025-02-12","cited_by_count":2,"area":"agents"},{"id":"2502.17036","title":"Language Model Re-rankers are Fooled by Lexical Similarities","created":"2025-02-24","cited_by_count":2,"area":"rag"},{"id":"2503.22727","title":"A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI","created":"2025-03-26","cited_by_count":2,"area":null},{"id":"2505.19489","title":"Taming System Complexity: Demystifying Software Engineering Agents in Diagnosing Linux Kernel Faults","created":"2025-05-26","cited_by_count":2,"area":"agents"},{"id":"2506.12494","title":"FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation","created":"2025-06-14","cited_by_count":2,"area":"rag"},{"id":"2510.11541","title":"Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation","created":"2025-10-13","cited_by_count":2,"area":"rag"},{"id":"2601.02522","title":"On the Effectiveness of Proposed Techniques to Reduce Energy Consumption in RAG Systems: A Controlled Experiment","created":"2026-01-05","cited_by_count":2,"area":"rag"},{"id":"2601.05549","title":"Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval","created":"2026-01-09","cited_by_count":2,"area":"lr"},{"id":"2605.12477","title":"MEME: Multi-entity & Evolving Memory Evaluation","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2504.05846","title":"PathGPT: Reframing Path Recommendation as a Natural Language Generation Task with Retrieval-Augmented Language Models","created":"2025-04-08","cited_by_count":1,"area":"rag"},{"id":"2504.18269","title":"TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation","created":"2025-04-25","cited_by_count":1,"area":null},{"id":"2505.13257","title":"Is Active Persona Inference Necessary for Aligning Small Models to Personal Preferences?","created":"2025-05-19","cited_by_count":1,"area":"alignment"},{"id":"2506.14407","title":"ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2508.08680","title":"TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translation","created":"2025-08-12","cited_by_count":1,"area":null},{"id":"2509.12677","title":"Case-Based Decision-Theoretic Decoding with Quality Memories","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2510.17476","title":"Zoom In Disparities in Healthcare LLM Q&A","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.10996","title":"MedBioRAG: Semantic Search and Retrieval-Augmented Generation with Large Language Models for Medical and Biological QA","created":"2025-12-10","cited_by_count":1,"area":"rag"},{"id":"2601.06458","title":"PixRec: Leveraging Visual Context for Next-Item Prediction in Sequential Recommendation","created":"2026-01-10","cited_by_count":1,"area":null},{"id":"2602.09616","title":"With Argus Eyes: Assessing Retrieval Gaps via Uncertainty Scoring to Detect and Remedy Retrieval Blind Spots","created":"2026-02-10","cited_by_count":1,"area":"rag"},{"id":"2602.23949","title":"HotelQuEST: Balancing Quality and Efficiency in Agentic Search","created":"2026-02-27","cited_by_count":1,"area":"agents"},{"id":"2603.12368","title":"Multi-Step Semantic Reasoning in Generative Retrieval","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2604.14473","title":"Response-Aware User Memory Selection for LLM Personalization","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.18508","title":"Document-as-Image Representations Fall Short for Scientific Retrieval","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.06006","title":"From Articles to Premises: Building PrimeFacts, an Extraction Methodology and Resource for Fact-Checking Evidence","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2606.18307","title":"DRIFT: Data Selection for LLM Instruction Tuning via On-Policy Attribution","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2411.13163","title":"Unlocking Historical Clinical Trial Data with ALIGN: A Compositional Large Language Model System for Medical Coding","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2412.20597","title":"GliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian","created":"2024-12-29","cited_by_count":0,"area":null},{"id":"2502.15692","title":"ACL-rlg: A Dataset for Reading List Generation","created":"2024-12-30","cited_by_count":0,"area":null},{"id":"2504.05125","title":"Interpretable Style Takagi-Sugeno-Kang Fuzzy Clustering","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2504.20679","title":"Are Information Retrieval Approaches Good at Harmonising Longitudinal Survey Questions in Social Science?","created":"2025-04-29","cited_by_count":0,"area":null},{"id":"2505.11582","title":"Comparing Lexical and Semantic Vector Search Methods When Classifying Medical Documents","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.12637","title":"How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2507.16011","title":"mRAKL: Multilingual Retrieval-Augmented Knowledge Graph Construction for Low-Resourced Languages","created":"2025-07-21","cited_by_count":0,"area":"rag"},{"id":"2510.00324","title":"Which Programming Language and Model Work Best With LLM-as-a-Judge For Code Retrieval?","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2602.04731","title":"Modular Expert Merging for Biomedical Retrieval","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.20990","title":"What Tracks Hard-Negative Transfer? A Study of Lexical and Semantic Signals","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2603.29002","title":"Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference","created":"2026-03-30","cited_by_count":0,"area":"rag"},{"id":"2605.00529","title":"Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation","created":"2026-05-01","cited_by_count":0,"area":"rag"},{"id":"2605.01399","title":"Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning","created":"2026-05-02","cited_by_count":0,"area":"lr"},{"id":"2605.04763","title":"How Does Chunking Affect Retrieval-Augmented Code Completion? A Controlled Empirical Study","created":"2026-05-06","cited_by_count":0,"area":"rag"},{"id":"2605.12028","title":"Caraman at SemEval-2026 Task 8: Three-Stage Multi-Turn Retrieval with Query Rewriting, Hybrid Search, and Cross-Encoder Reranking","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.12313","title":"Overview of the MedHopQA track at BioCreative IX: track description, participation and evaluation of systems for multi-hop medical question answering","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.17379","title":"Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.18561","title":"Improving BM25 Code Retrieval Under Fixed Generic Tokenization: Adaptive q-Log Odds as a Drop-In BM25 Fix","created":"2026-05-18","cited_by_count":0,"area":"rag"},{"id":"2605.30487","title":"Configurable Reward Model for Balanced Safety Alignment","created":"2026-05-28","cited_by_count":0,"area":"alignment"},{"id":"2606.17255","title":"MLLP-VRAIN UPV system for the IWSLT 2026 Simultaneous Speech Translation task","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.05927","title":"CMDR: Contextual Multimodal Document Retrieval","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.18603","title":"AutoIndex: Learning Representation Programs for Retrieval","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.21936","title":"Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models","created":"2026-07-24","cited_by_count":0,"area":"rag"},{"id":"2608.27394","title":"RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.10745","title":"Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking","created":"2026-09-09","cited_by_count":0,"area":"lr"},{"id":"2609.18908","title":"How Much is a Human Right Worth? ECtHR-NPD: A Benchmark for Predicting Non-Pecuniary Damage Awards","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.20754","title":"RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents","created":"2026-09-17","cited_by_count":0,"area":"rag"},{"id":"2609.36534","title":"Retrieval Sensitivity to Identity Signals in Queries","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}