{"total":118,"rows":[{"id":"2402.17753","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","created":"2024-02-27","cited_by_count":830,"area":"agents"},{"id":"2401.08281","title":"The Faiss library","created":"2024-01-16","cited_by_count":376,"area":null},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206,"area":"agents"},{"id":"2407.02485","title":"RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs","created":"2024-07-02","cited_by_count":202,"area":"rag"},{"id":"2402.04617","title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","created":"2024-02-07","cited_by_count":197,"area":"agents"},{"id":"2310.01352","title":"RA-DIT: Retrieval-Augmented Dual Instruction Tuning","created":"2023-10-02","cited_by_count":195,"area":"rag"},{"id":"2411.02571","title":"MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs","created":"2024-11-04","cited_by_count":161,"area":"mllm"},{"id":"2405.13792","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","created":"2024-05-22","cited_by_count":125,"area":"rag"},{"id":"2407.16833","title":"Retrieval Augmented Generation or Long-Context LLMs? A Comprehensive Study and Hybrid Approach","created":"2024-07-23","cited_by_count":119,"area":"rag"},{"id":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115,"area":null},{"id":"2401.10225","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","created":"2024-01-18","cited_by_count":90,"area":"rag"},{"id":"2312.06648","title":"Dense X Retrieval: What Retrieval Granularity Should We Use?","created":"2023-12-11","cited_by_count":88,"area":null},{"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":"2407.12854","title":"Scaling Retrieval-Based Language Models with a Trillion-Token Datastore","created":"2024-07-09","cited_by_count":56,"area":null},{"id":"2310.07713","title":"InstructRetro: Instruction Tuning post Retrieval-Augmented Pretraining","created":"2023-10-11","cited_by_count":53,"area":"rag"},{"id":"2407.14482","title":"ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities","created":"2024-07-19","cited_by_count":53,"area":"rag"},{"id":"2405.01525","title":"FLAME: Factuality-Aware Alignment for Large Language Models","created":"2024-05-02","cited_by_count":47,"area":"alignment"},{"id":"2310.13243","title":"Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking","created":"2023-10-20","cited_by_count":44,"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":"2404.06347","title":"RAR-b: Reasoning as Retrieval Benchmark","created":"2024-04-09","cited_by_count":36,"area":"lr"},{"id":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31,"area":"rag"},{"id":"2309.08872","title":"PDFTriage: Question Answering over Long, Structured Documents","created":"2023-09-16","cited_by_count":29,"area":null},{"id":"2410.17952","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains","created":"2024-10-23","cited_by_count":28,"area":"rag"},{"id":"2404.19543","title":"RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processing","created":"2024-04-30","cited_by_count":25,"area":"rag"},{"id":"2405.19325","title":"Nearest Neighbor Speculative Decoding for LLM Generation and Attribution","created":"2024-05-29","cited_by_count":25,"area":"inference"},{"id":"2311.05800","title":"Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval","created":"2023-11-10","cited_by_count":24,"area":null},{"id":"2502.13668","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","created":"2025-02-19","cited_by_count":22,"area":null},{"id":"2403.00815","title":"RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records","created":"2024-02-25","cited_by_count":21,"area":null},{"id":"2504.04915","title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration","created":"2025-04-07","cited_by_count":20,"area":"lr"},{"id":"2502.18460","title":"DRAMA: Diverse Augmentation from Large Language Models to Smaller Dense Retrievers","created":"2025-02-25","cited_by_count":19,"area":null},{"id":"2310.20158","title":"GAR-meets-RAG Paradigm for Zero-Shot Information Retrieval","created":"2023-10-31","cited_by_count":18,"area":null},{"id":"2602.16173","title":"Learning Personalized Agents from Human Feedback","created":"2026-02-18","cited_by_count":18,"area":"alignment"},{"id":"2402.07092","title":"Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation","created":"2024-02-11","cited_by_count":17,"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":"2503.12600","title":"GraphEval: A Lightweight Graph-Based LLM Framework for Idea Evaluation","created":"2025-03-16","cited_by_count":17,"area":null},{"id":"2406.11460","title":"TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation","created":"2024-06-17","cited_by_count":16,"area":"lr"},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16,"area":"rag"},{"id":"2502.16636","title":"Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries","created":"2025-02-23","cited_by_count":16,"area":"rag"},{"id":"2503.05037","title":"Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence","created":"2025-03-06","cited_by_count":16,"area":"rag"},{"id":"2507.10539","title":"Graph World Model","created":"2025-07-14","cited_by_count":16,"area":"wm"},{"id":"2410.22353","title":"RuleRAG: Rule-Guided Retrieval-Augmented Generation with Language Models for Question Answering","created":"2024-10-15","cited_by_count":13,"area":"rag"},{"id":"2307.08303","title":"Soft Prompt Tuning for Augmenting Dense Retrieval with Large Language Models","created":"2023-07-17","cited_by_count":12,"area":null},{"id":"2402.11035","title":"Dense Passage Retrieval: Is it Retrieving?","created":"2024-02-16","cited_by_count":12,"area":"rag"},{"id":"2409.02685","title":"RouterRetriever: Routing over a Mixture of Expert Embedding Models","created":"2024-09-04","cited_by_count":12,"area":"moe"},{"id":"2410.11001","title":"Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs","created":"2024-10-14","cited_by_count":12,"area":"rag"},{"id":"2407.07799","title":"Attribute or Abstain: Large Language Models as Long Document Assistants","created":"2024-07-10","cited_by_count":11,"area":null},{"id":"2504.17884","title":"Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense Retrieval","created":"2025-04-24","cited_by_count":11,"area":null},{"id":"2510.10397","title":"AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval","created":"2025-10-12","cited_by_count":11,"area":null},{"id":"2602.01885","title":"ES-MemEval: Benchmarking Conversational Agents on Personalized Long-Term Emotional Support","created":"2026-02-02","cited_by_count":11,"area":"agents"},{"id":"2402.13542","title":"ARL2: Aligning Retrievers for Black-box Large Language Models via Self-guided Adaptive Relevance Labeling","created":"2024-02-21","cited_by_count":10,"area":"rag"},{"id":"2509.18436","title":"Memory-QA: Answering Recall Questions Based on Multimodal Memories","created":"2025-09-22","cited_by_count":10,"area":null},{"id":"2305.13691","title":"Few-Shot Data Synthesis for Open Domain Multi-Hop Question Answering","created":"2023-05-23","cited_by_count":9,"area":"synth"},{"id":"2407.10691","title":"$\\texttt{MixGR}$: Enhancing Retriever Generalization for Scientific Domain through Complementary Granularity","created":"2024-07-15","cited_by_count":9,"area":null},{"id":"2509.01092","title":"REFRAG: Rethinking RAG based Decoding","created":"2025-09-01","cited_by_count":9,"area":"lr"},{"id":"2409.04593","title":"Paper Copilot: A Self-Evolving and Efficient LLM System for Personalized Academic Assistance","created":"2024-09-06","cited_by_count":8,"area":"synth"},{"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":"2410.03780","title":"Reward-RAG: Enhancing RAG with Reward Driven Supervision","created":"2024-10-03","cited_by_count":7,"area":"rag"},{"id":"2501.04802","title":"Reproducing HotFlip for Corpus Poisoning Attacks in Dense Retrieval","created":"2025-01-08","cited_by_count":7,"area":null},{"id":"2502.05364","title":"Hypencoder: Hypernetworks for Information Retrieval","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2404.05825","title":"LLM-Augmented Retrieval: Enhancing Retrieval Models Through Language Models and Doc-Level Embedding","created":"2024-04-08","cited_by_count":6,"area":null},{"id":"2504.03101","title":"Single-Pass Document Scanning for Question Answering","created":"2025-04-04","cited_by_count":6,"area":null},{"id":"2505.07793","title":"Overflow Prevention Enhances Long-Context Recurrent LLMs","created":"2025-05-12","cited_by_count":6,"area":"ssm"},{"id":"2506.04565","title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","created":"2025-06-05","cited_by_count":6,"area":null},{"id":"2506.17336","title":"PPMI: Privacy-Preserving LLM Interaction with Socratic Chain-of-Thought Reasoning and Homomorphically Encrypted Vector Databases","created":"2025-06-19","cited_by_count":6,"area":"lr"},{"id":"2306.11550","title":"Query Encoder Distillation via Embedding Alignment is a Strong Baseline Method to Boost Dense Retriever Online Efficiency","created":"2023-06-05","cited_by_count":5,"area":null},{"id":"2406.16013","title":"Database-Augmented Query Representation for Information Retrieval","created":"2024-06-23","cited_by_count":5,"area":null},{"id":"2407.04528","title":"GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning","created":"2024-07-05","cited_by_count":5,"area":"rag"},{"id":"2410.14881","title":"Class-RAG: Real-Time Content Moderation with Retrieval Augmented Generation","created":"2024-10-18","cited_by_count":5,"area":"rag"},{"id":"2412.15189","title":"Face the Facts! Evaluating RAG-based Pipelines for Professional Fact-Checking","created":"2024-12-19","cited_by_count":5,"area":null},{"id":"2504.05216","title":"Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling","created":"2025-04-07","cited_by_count":5,"area":null},{"id":"2311.15564","title":"Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval","created":"2023-11-27","cited_by_count":4,"area":null},{"id":"2406.08116","title":"Supportiveness-based Knowledge Rewriting for Retrieval-augmented Language Modeling","created":"2024-06-12","cited_by_count":4,"area":"rag"},{"id":"2408.15491","title":"Enhancing and Accelerating Large Language Models via Instruction-Aware Contextual Compression","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2506.09200","title":"FedRAG: A Framework for Fine-Tuning Retrieval-Augmented Generation Systems","created":"2025-06-10","cited_by_count":4,"area":"rag"},{"id":"2507.22337","title":"A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2510.17725","title":"AcademicEval: Live Long-Context LLM Benchmark","created":"2025-10-20","cited_by_count":4,"area":null},{"id":"2409.05677","title":"RIRAG: Regulatory Information Retrieval and Answer Generation","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2410.01383","title":"PairDistill: Pairwise Relevance Distillation for Dense Retrieval","created":"2024-10-02","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":"2505.17086","title":"Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning","created":"2025-05-20","cited_by_count":3,"area":"rag"},{"id":"2508.04057","title":"PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG","created":"2025-08-06","cited_by_count":3,"area":"rag"},{"id":"2601.03908","title":"Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval","created":"2026-01-07","cited_by_count":3,"area":"rag"},{"id":"2305.11744","title":"ReFIT: Relevance Feedback from a Reranker during Inference","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2410.02825","title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","created":"2024-09-30","cited_by_count":2,"area":null},{"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":"2311.09765","title":"Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in Dense Encoders","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2502.10596","title":"Post-training an LLM for RAG? Train on Self-Generated Demonstrations","created":"2025-02-14","cited_by_count":1,"area":"rag"},{"id":"2506.14407","title":"ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2507.21142","title":"Privacy Artifact ConnecTor (PACT): Embedding Enterprise Artifacts for Compliance AI Agents","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2507.23070","title":"Vocabulary-free Fine-grained Visual Recognition via Enriched Contextually Grounded Vision-Language Model","created":"2025-07-30","cited_by_count":1,"area":"mllm"},{"id":"2510.00919","title":"Benchmarking Foundation Models with Retrieval-Augmented Generation in Olympic-Level Physics Problem Solving","created":"2025-10-01","cited_by_count":1,"area":"rag"},{"id":"2601.11913","title":"LSTM-MAS: A Long Short-Term Memory Inspired Multi-Agent System for Long-Context Understanding","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2602.09448","title":"The Wisdom of Many Queries: Complexity-Diversity Principle for Dense Retriever Training","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.07041","title":"AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views","created":"2026-04-08","cited_by_count":1,"area":"agents"},{"id":"2604.12231","title":"Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems","created":"2026-04-14","cited_by_count":1,"area":"lr"},{"id":"2605.00505","title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","created":"2026-05-01","cited_by_count":1,"area":"rag"},{"id":"2609.18262","title":"REPAIR: Resolving Long-Tail Confusion in Scientific Retrievers via Fact-Verified Iterative Refinement","created":"2026-09-16","cited_by_count":1,"area":null},{"id":"2405.01924","title":"Semi-Parametric Retrieval via Binary Bag-of-Tokens Index","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2410.04790","title":"PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QA","created":"2024-10-07","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}