{"total":265,"rows":[{"id":"2412.13663","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","created":"2024-12-18","cited_by_count":554,"area":null},{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"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":"2406.10252","title":"AutoSurvey: Large Language Models Can Automatically Write Surveys","created":"2024-06-10","cited_by_count":119,"area":null},{"id":"2406.15319","title":"LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs","created":"2024-06-21","cited_by_count":108,"area":"rag"},{"id":"2504.20595","title":"ReasonIR: Training Retrievers for Reasoning Tasks","created":"2025-04-29","cited_by_count":77,"area":"lr"},{"id":"2409.04701","title":"Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models","created":"2024-09-07","cited_by_count":73,"area":null},{"id":"2405.05374","title":"Arctic-Embed: Scalable, Efficient, and Accurate Text Embedding Models","created":"2024-05-08","cited_by_count":61,"area":null},{"id":"2412.04506","title":"Arctic-Embed 2.0: Multilingual Retrieval Without Compromise","created":"2024-12-03","cited_by_count":58,"area":null},{"id":"2502.06864","title":"Knowledge Graph-Guided Retrieval Augmented Generation","created":"2025-02-08","cited_by_count":58,"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":"2502.11371","title":"RAG vs. GraphRAG: A Systematic Evaluation and Key Insights","created":"2025-02-17","cited_by_count":53,"area":"rag"},{"id":"2404.12096","title":"LongEmbed: Extending Embedding Models for Long Context Retrieval","created":"2024-04-18","cited_by_count":48,"area":null},{"id":"2505.05568","title":"Griffin: Towards a Graph-Centric Relational Database Foundation Model","created":"2025-05-08","cited_by_count":47,"area":null},{"id":"2404.04656","title":"Binary Classifier Optimization for Large Language Model Alignment","created":"2024-04-06","cited_by_count":45,"area":"alignment"},{"id":"2410.04585","title":"Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval","created":"2024-10-06","cited_by_count":45,"area":"lr"},{"id":"2509.06888","title":"mmBERT: A Modern Multilingual Encoder with Annealed Language Learning","created":"2025-09-08","cited_by_count":45,"area":null},{"id":"2408.01107","title":"BioRAG: A RAG-LLM Framework for Biological Question Reasoning","created":"2024-08-02","cited_by_count":43,"area":"lr"},{"id":"2507.11412","title":"Seq vs Seq: An Open Suite of Paired Encoders and Decoders","created":"2025-07-15","cited_by_count":38,"area":null},{"id":"2412.01007","title":"CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking","created":"2024-12-01","cited_by_count":37,"area":null},{"id":"2502.17125","title":"LettuceDetect: A Hallucination Detection Framework for RAG Applications","created":"2025-02-24","cited_by_count":34,"area":"rag"},{"id":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"id":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31,"area":"rag"},{"id":"2409.08045","title":"Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking","created":"2024-09-12","cited_by_count":30,"area":"safety"},{"id":"2502.09891","title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","created":"2025-02-14","cited_by_count":28,"area":"rag"},{"id":"2503.01776","title":"Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2402.07440","title":"Benchmarking and Building Long-Context Retrieval Models with LoCo and M2-BERT","created":"2024-02-12","cited_by_count":21,"area":null},{"id":"2409.09603","title":"Towards Data-Centric RLHF: Simple Metrics for Preference Dataset Comparison","created":"2024-09-15","cited_by_count":21,"area":"alignment"},{"id":"2510.01149","title":"ModernVBERT: Towards Smaller Visual Document Retrievers","created":"2025-10-01","cited_by_count":21,"area":"rag"},{"id":"2404.07900","title":"High-Dimension Human Value Representation in Large Language Models","created":"2024-04-11","cited_by_count":20,"area":null},{"id":"2505.07849","title":"SweRank: Software Issue Localization with Code Ranking","created":"2025-05-07","cited_by_count":20,"area":null},{"id":"2406.01607","title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark","created":"2024-05-27","cited_by_count":19,"area":null},{"id":"2406.18587","title":"Nomic Embed Vision: Expanding the Latent Space","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2410.02525","title":"Contextual Document Embeddings","created":"2024-10-03","cited_by_count":19,"area":null},{"id":"2410.02902","title":"Better Instruction-Following Through Minimum Bayes Risk","created":"2024-10-03","cited_by_count":19,"area":null},{"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":"2508.03555","title":"PyLate: Flexible Training and Retrieval for Late Interaction Models","created":"2025-08-05","cited_by_count":18,"area":null},{"id":"2407.18887","title":"Embedding And Clustering Your Data Can Improve Contrastive Pretraining","created":"2024-07-26","cited_by_count":17,"area":null},{"id":"2407.19619","title":"Enhancing Code Translation in Language Models with Few-Shot Learning via Retrieval-Augmented Generation","created":"2024-07-29","cited_by_count":16,"area":"rag"},{"id":"2502.10996","title":"RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2504.10471","title":"MIEB: Massive Image Embedding Benchmark","created":"2025-04-14","cited_by_count":15,"area":null},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2406.11938","title":"Tracking the perspectives of interacting language models","created":"2024-06-17","cited_by_count":14,"area":null},{"id":"2507.00014","title":"SWE-Bench-CL: Continual Learning for Coding Agents","created":"2025-06-13","cited_by_count":14,"area":"agents"},{"id":"2407.21048","title":"APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generation","created":"2024-07-23","cited_by_count":12,"area":null},{"id":"2409.14254","title":"Instruction Following without Instruction Tuning","created":"2024-09-21","cited_by_count":12,"area":null},{"id":"2412.00532","title":"ChemTEB: Chemical Text Embedding Benchmark, an Overview of Embedding Models Performance & Efficiency on a Specific Domain","created":"2024-11-30","cited_by_count":12,"area":null},{"id":"2504.08716","title":"ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance","created":"2025-04-11","cited_by_count":12,"area":null},{"id":"2504.08762","title":"InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System","created":"2025-03-31","cited_by_count":12,"area":null},{"id":"2502.03824","title":"Syntriever: How to Train Your Retriever with Synthetic Data from LLMs","created":"2025-02-06","cited_by_count":11,"area":"synth"},{"id":"2504.08231","title":"Out of Style: RAG's Fragility to Linguistic Variation","created":"2025-04-11","cited_by_count":11,"area":"rag"},{"id":"2506.01435","title":"Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings","created":"2025-06-02","cited_by_count":11,"area":null},{"id":"2508.05318","title":"mKG-RAG: Leveraging Multimodal Knowledge Graphs in Retrieval-Augmented Generation for Knowledge-intensive VQA","created":"2025-08-07","cited_by_count":11,"area":"mllm"},{"id":"2409.17308","title":"Consistent estimation of generative model representations in the data kernel perspective space","created":"2024-09-25","cited_by_count":10,"area":"diffusion"},{"id":"2502.17057","title":"ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance","created":"2025-02-24","cited_by_count":10,"area":null},{"id":"2504.07199","title":"SemEval-2025 Task 5: LLMs4Subjects -- LLM-based Automated Subject Tagging for a National Technical Library's Open-Access Catalog","created":"2025-04-09","cited_by_count":10,"area":null},{"id":"2410.01106","title":"Statistical inference on black-box generative models in the data kernel perspective space","created":"2024-10-01","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":"2602.07491","title":"GraphAgents: Knowledge Graph-Guided Agentic AI for Cross-Domain Materials Design","created":"2026-02-07","cited_by_count":9,"area":"agents"},{"id":"2604.15597","title":"LLMs Corrupt Your Documents When You Delegate","created":"2026-04-17","cited_by_count":9,"area":null},{"id":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2508.01959","title":"SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension","created":"2025-08-03","cited_by_count":8,"area":"rag"},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","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":"2510.26012","title":"AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys","created":"2025-10-29","cited_by_count":8,"area":null},{"id":"2605.22645","title":"AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters","created":"2026-05-21","cited_by_count":8,"area":"mllm"},{"id":"2501.19264","title":"mFollowIR: a Multilingual Benchmark for Instruction Following in Retrieval","created":"2025-01-31","cited_by_count":7,"area":null},{"id":"2504.02268","title":"Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Data","created":"2025-04-03","cited_by_count":7,"area":null},{"id":"2506.09114","title":"TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval","created":"2025-06-10","cited_by_count":7,"area":null},{"id":"2509.20175","title":"Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI","created":"2025-09-24","cited_by_count":7,"area":"agents"},{"id":"2510.21900","title":"Deep Literature Survey Automation with an Iterative Workflow","created":"2025-10-24","cited_by_count":7,"area":null},{"id":"2405.13517","title":"WaterPool: A Watermark Mitigating Trade-offs among Imperceptibility, Efficacy and Robustness","created":"2024-05-22","cited_by_count":6,"area":null},{"id":"2410.15262","title":"HyQE: Ranking Contexts with Hypothetical Query Embeddings","created":"2024-10-20","cited_by_count":6,"area":"rag"},{"id":"2412.15272","title":"SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation","created":"2024-12-17","cited_by_count":6,"area":"rag"},{"id":"2502.10177","title":"STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2505.17810","title":"VIBE: Vector Index Benchmark for Embeddings","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2506.17277","title":"Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation","created":"2025-06-13","cited_by_count":6,"area":"rag"},{"id":"2603.29199","title":"AEC-Bench: A Multimodal Benchmark for Agentic Systems in Architecture, Engineering, and Construction","created":"2026-03-31","cited_by_count":6,"area":"agents"},{"id":"2406.05326","title":"Advancing Semantic Textual Similarity Modeling: A Regression Framework with Translated ReLU and Smooth K2 Loss","created":"2024-06-08","cited_by_count":5,"area":null},{"id":"2406.09790","title":"Pcc-tuning: Breaking the Contrastive Learning Ceiling in Semantic Textual Similarity","created":"2024-06-14","cited_by_count":5,"area":null},{"id":"2501.18280","title":"Jailbreaking LLMs' Safeguard with Universal Magic Words for Text Embedding Models","created":"2025-01-30","cited_by_count":5,"area":"safety"},{"id":"2506.00037","title":"Query Drift Compensation: Enabling Compatibility in Continual Learning of Retrieval Embedding Models","created":"2025-05-27","cited_by_count":5,"area":"rag"},{"id":"2508.01643","title":"ChEmbed: Enhancing Chemical Literature Search Through Domain-Specific Text Embeddings","created":"2025-08-03","cited_by_count":5,"area":"rag"},{"id":"2508.14317","title":"SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing","created":"2025-08-20","cited_by_count":5,"area":null},{"id":"2511.03878","title":"KnowThyself: An Agentic Assistant for LLM Interpretability","created":"2025-11-05","cited_by_count":5,"area":"agents"},{"id":"2512.17220","title":"Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding","created":"2025-12-19","cited_by_count":5,"area":"rag"},{"id":"2601.01684","title":"LACONIC: Dense-Level Effectiveness for Scalable Sparse Retrieval via a Two-Phase Training Curriculum","created":"2026-01-04","cited_by_count":5,"area":null},{"id":"2602.15344","title":"ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2605.31580","title":"Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings","created":"2026-05-29","cited_by_count":5,"area":null},{"id":"2408.10437","title":"Understanding Generative AI Content with Embedding Models","created":"2024-08-19","cited_by_count":4,"area":null},{"id":"2412.05159","title":"Enhancing Cross-Language Code Translation via Task-Specific Embedding Alignment in Retrieval-Augmented Generation","created":"2024-12-06","cited_by_count":4,"area":"rag"},{"id":"2412.15241","title":"Quantifying Positional Biases in Text Embedding Models","created":"2024-12-13","cited_by_count":4,"area":null},{"id":"2502.15854","title":"Enhancing Domain-Specific Retrieval-Augmented Generation: Synthetic Data Generation and Evaluation using Reasoning Models","created":"2025-02-21","cited_by_count":4,"area":"lr"},{"id":"2503.19800","title":"SemEval-2025 Task 9: The Food Hazard Detection Challenge","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2505.11388","title":"The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2507.21110","title":"SemRAG: Semantic Knowledge-Augmented RAG for Improved Question-Answering","created":"2025-07-10","cited_by_count":4,"area":"rag"},{"id":"2507.22917","title":"Reading Between the Timelines: RAG for Answering Diachronic Questions","created":"2025-07-21","cited_by_count":4,"area":"rag"},{"id":"2512.05013","title":"Detecting Perspective Shifts in Multi-agent Systems","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2602.16609","title":"ColBERT-Zero: To Pre-train Or Not To Pre-train ColBERT models","created":"2026-02-18","cited_by_count":4,"area":"distill"},{"id":"2502.09532","title":"Mind the Gap! Choice Independence in Using Multilingual LLMs for Persuasive Co-Writing Tasks in Different Languages","created":"2025-02-13","cited_by_count":3,"area":null}],"next_cursor":"100"}