{"total":67,"rows":[{"id":"2402.01613","title":"Nomic Embed: Training a Reproducible Long Context Text Embedder","created":"2024-02-02","cited_by_count":265,"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":"2402.09906","title":"Generative Representational Instruction Tuning","created":"2024-02-15","cited_by_count":233,"area":null},{"id":"2409.10173","title":"jina-embeddings-v3: Multilingual Embeddings With Task LoRA","created":"2024-09-16","cited_by_count":141,"area":null},{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76,"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":"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":"2405.20204","title":"Jina CLIP: Your CLIP Model Is Also Your Text Retriever","created":"2024-05-30","cited_by_count":46,"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":"2408.16672","title":"Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever","created":"2024-08-29","cited_by_count":25,"area":null},{"id":"2402.14526","title":"Balanced Data Sampling for Language Model Training with Clustering","created":"2024-02-22","cited_by_count":23,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2402.17016","title":"Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings","created":"2024-02-26","cited_by_count":21,"area":null},{"id":"2406.14848","title":"Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models","created":"2024-06-21","cited_by_count":20,"area":null},{"id":"2409.15240","title":"MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation","created":"2024-09-23","cited_by_count":15,"area":null},{"id":"2504.13128","title":"FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents","created":"2025-04-17","cited_by_count":15,"area":null},{"id":"2508.21290","title":"Efficient Code Embeddings from Code Generation Models","created":"2025-08-29","cited_by_count":13,"area":null},{"id":"2412.13102","title":"AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark","created":"2024-12-17","cited_by_count":12,"area":null},{"id":"2411.04997","title":"LLM2CLIP: Powerful Language Model Unlocks Richer Cross-Modality Representation","created":"2024-11-07","cited_by_count":11,"area":null},{"id":"2506.08354","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","created":"2025-06-10","cited_by_count":10,"area":null},{"id":"2510.12709","title":"SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model","created":"2025-10-14","cited_by_count":10,"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":"2602.11151","title":"Diffusion-Pretrained Dense and Contextual Embeddings","created":"2026-02-11","cited_by_count":9,"area":null},{"id":"2401.01943","title":"Generalist embedding models are better at short-context clinical semantic search than specialized embedding models","created":"2024-01-03","cited_by_count":7,"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":"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":"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":"2507.11083","title":"Function-to-Style Guidance of LLMs for Code Translation","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2507.13105","title":"SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts","created":"2025-07-17","cited_by_count":4,"area":null},{"id":"2511.00125","title":"Inferring multiple helper Dafny assertions with LLMs","created":"2025-10-31","cited_by_count":4,"area":null},{"id":"2603.01714","title":"TopoCurate:Modeling Interaction Topology for Tool-Use Agent Training","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2412.13859","title":"Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models","created":"2024-12-18","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":"2604.08115","title":"Revise: A Framework for Revising OCRed text in Practical Information Systems with Data Contamination Strategy","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2409.07737","title":"Ruri: Japanese General Text Embeddings","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2412.06136","title":"AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2509.26136","title":"CliniBench: A Clinical Outcome Prediction Benchmark for Generative and Encoder-Based Language Models","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2411.12880","title":"Advancing Large Language Models for Spatiotemporal and Semantic Association Mining of Similar Environmental Events","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2502.15996","title":"Med-gte-hybrid: A contextual embedding transformer model for extracting actionable information from clinical texts","created":"2025-02-21","cited_by_count":1,"area":null},{"id":"2502.20399","title":"Momentum Posterior Regularization for Multi-hop Dense Retrieval","created":"2024-12-17","cited_by_count":1,"area":null},{"id":"2503.06734","title":"Gender Encoding Patterns in Pretrained Language Model Representations","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2509.00141","title":"Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2509.18775","title":"Financial Risk Relation Identification through Dual-view Adaptation","created":"2025-09-23","cited_by_count":1,"area":null},{"id":"2511.22651","title":"Automated Design Optimization via Strategic Search with Large Language Models","created":"2025-11-27","cited_by_count":1,"area":null},{"id":"2603.14257","title":"Automatic Inter-document Multi-hop Scientific QA Generation","created":"2026-03-15","cited_by_count":1,"area":null},{"id":"2606.19719","title":"Closing the Operational Gap in Semantic Caching","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2311.09748","title":"Translation Aligned Sentence Embeddings for Turkish Language","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2405.11461","title":"DocReLM: Mastering Document Retrieval with Language Model","created":"2024-05-19","cited_by_count":0,"area":null},{"id":"2412.12649","title":"ClustEm4Ano: Clustering Text Embeddings of Nominal Textual Attributes for Microdata Anonymization","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2506.03822","title":"CRAWLDoc: A Dataset for Robust Ranking of Bibliographic Documents","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2507.01049","title":"Cohort Retrieval using Dense Passage Retrieval","created":"2025-06-26","cited_by_count":0,"area":null},{"id":"2507.03415","title":"SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation","created":"2025-07-04","cited_by_count":0,"area":null},{"id":"2511.19739","title":"Comparative Analysis of LoRA-Adapted Embedding Models for Clinical Cardiology Text Representation","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.07100","title":"Dual Refinement Cycle Learning: Unsupervised Text Classification of Mamba and Community Detection on Text Attributed Graph","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.06877","title":"Personality-Aware Reinforcement Learning for Persuasive Dialogue with LLM-Driven Simulation","created":"2026-01-11","cited_by_count":0,"area":null},{"id":"2602.00911","title":"Synapse: Federated Tool Routing via Typed Compendium Artifacts","created":"2026-01-31","cited_by_count":0,"area":null},{"id":"2602.04812","title":"Robust Generalizable Heterogeneous Legal Link Prediction","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2605.05251","title":"Identifier-Free Code Embedding Models for Scalable Search","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.03027","title":"SEA-LION-Embedding: Open and Reproducible Text Embeddings for Southeast Asia","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2608.03994","title":"When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.28048","title":"TEMPS: Temporal Sentence Embeddings for Temporal Information Retrieval","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.31595","title":"GraphWrit3R: End-to-End 3D Scene Graph Writing","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.37782","title":"Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.20588","title":"Your Transformer Is Secretly Elastic","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}