{"total":166,"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":"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":"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":"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":"2509.06888","title":"mmBERT: A Modern Multilingual Encoder with Annealed Language Learning","created":"2025-09-08","cited_by_count":45,"area":null},{"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":"2412.12591","title":"LLMs are Also Effective Embedding Models: An In-depth Overview","created":"2024-12-17","cited_by_count":32,"area":null},{"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":"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":"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":"2406.11938","title":"Tracking the perspectives of interacting language models","created":"2024-06-17","cited_by_count":14,"area":null},{"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":"2506.01435","title":"Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings","created":"2025-06-02","cited_by_count":11,"area":null},{"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":"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":"2508.21085","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":"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":"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":"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":"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":"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":"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":"2412.15241","title":"Quantifying Positional Biases in Text Embedding Models","created":"2024-12-13","cited_by_count":4,"area":null},{"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":"2512.05013","title":"Detecting Perspective Shifts in Multi-agent Systems","created":"2025-12-04","cited_by_count":4,"area":null},{"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},{"id":"2502.17541","title":"Dataset Featurization: Uncovering Natural Language Features through Unsupervised Data Reconstruction","created":"2025-02-24","cited_by_count":3,"area":null},{"id":"2505.00358","title":"R&B: Domain Regrouping and Data Mixture Balancing for Efficient Foundation Model Training","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2505.18607","title":"From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2506.12895","title":"Assessing the Performance Gap Between Lexical and Semantic Models for Information Retrieval With Formulaic Legal Language","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2510.04441","title":"Domain Generalization Under Posterior Drift","created":"2025-10-06","cited_by_count":3,"area":null},{"id":"2605.11325","title":"Structured Belief State and the First Precision-Aware Benchmark for LLM Memory Retrieval","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2607.01977","title":"OntoLearner: A Modular Python Library for Ontology Learning with Large Language Models","created":"2026-07-02","cited_by_count":3,"area":null},{"id":"2402.17682","title":"NextLevelBERT: Masked Language Modeling with Higher-Level Representations for Long Documents","created":"2024-02-27","cited_by_count":2,"area":null},{"id":"2402.18385","title":"The First Place Solution of WSDM Cup 2024: Leveraging Large Language Models for Conversational Multi-Doc QA","created":"2024-02-28","cited_by_count":2,"area":null},{"id":"2403.10318","title":"pTNAS: Progressive Neural Architecture Search for Tabular Data","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2409.06416","title":"Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2409.07737","title":"Ruri: Japanese General Text Embeddings","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2410.07173","title":"Better Language Models Exhibit Higher Visual Alignment","created":"2024-10-09","cited_by_count":2,"area":null},{"id":"2504.13443","title":"Trust, but verify","created":"2025-04-18","cited_by_count":2,"area":null},{"id":"2505.08435","title":"Hakim: Farsi Text Embedding Model","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2505.14543","title":"Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2505.15696","title":"MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.00077","title":"Gaussian mixture models as a proxy for interacting language models","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2506.13163","title":"Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback","created":"2025-06-16","cited_by_count":2,"area":null},{"id":"2507.19407","title":"Towards Domain Specification of Embedding Models in Medicine","created":"2025-07-25","cited_by_count":2,"area":null},{"id":"2508.02720","title":"ECGTwin: Personalized ECG Generation Using Controllable Diffusion Model","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2508.17400","title":"Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2509.17671","title":"Turk-LettuceDetect: A Hallucination Detection Models for Turkish RAG Applications","created":"2025-09-22","cited_by_count":2,"area":null},{"id":"2510.13406","title":"When Embedding Models Meet: Procrustes Bounds and Applications","created":"2025-10-15","cited_by_count":2,"area":null},{"id":"2510.20279","title":"ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2512.12880","title":"Improving Recursive Transformers with Mixture of LoRAs","created":"2025-12-14","cited_by_count":2,"area":null},{"id":"2512.19475","title":"A Large-Language-Model Framework for Automated Humanitarian Situation Reporting","created":"2025-12-22","cited_by_count":2,"area":null},{"id":"2604.27398","title":"Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2606.02488","title":"RASER: Recoverability-Aware Selective Escalation Router for Multi-Hop Question Answering","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2408.05911","title":"A New Pipeline For Generating Instruction Dataset via RAG and Self Fine-Tuning","created":"2024-08-12","cited_by_count":1,"area":null},{"id":"2409.18596","title":"ASAG2024: A Combined Benchmark for Short Answer Grading","created":"2024-09-27","cited_by_count":1,"area":null},{"id":"2503.16439","title":"DreamLLM-3D: Affective Dream Reliving using Large Language Model and 3D Generative AI","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2505.00006","title":"Toward a digital twin of U.S. Congress","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2506.02527","title":"Multilingual Information Retrieval with a Monolingual Knowledge Base","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.12189","title":"Supernova Event Dataset: Interpreting Large Language Models' Personality through Critical Event Analysis","created":"2025-06-13","cited_by_count":1,"area":null},{"id":"2506.21288","title":"Small Encoders Can Rival Large Decoders in Detecting Groundedness","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2508.04683","title":"Query Attribute Modeling: Improving search relevance with Semantic Search and Meta Data Filtering","created":"2025-08-06","cited_by_count":1,"area":null},{"id":"2510.21891","title":"Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2510.22369","title":"GigaEmbeddings: Efficient Russian Language Embedding Model","created":"2025-10-25","cited_by_count":1,"area":null}],"next_cursor":"100"}