{"total":118,"rows":[{"id":"2402.03216","title":"M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation","created":"2024-02-05","cited_by_count":1073,"area":"distill"},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723,"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":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192,"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":"2302.07452","title":"How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval","created":"2023-02-15","cited_by_count":118,"area":null},{"id":"2210.10634","title":"RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses","created":"2022-10-12","cited_by_count":115,"area":null},{"id":"2310.19923","title":"Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents","created":"2023-10-30","cited_by_count":104,"area":null},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79,"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":"2407.02883","title":"CoIR: A Comprehensive Benchmark for Code Information Retrieval Models","created":"2024-07-03","cited_by_count":60,"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":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2505.16470","title":"Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering","created":"2025-05-22","cited_by_count":36,"area":"rag"},{"id":"2306.03166","title":"Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training","created":"2023-06-05","cited_by_count":35,"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":"2407.01102","title":"BERGEN: A Benchmarking Library for Retrieval-Augmented Generation","created":"2024-07-01","cited_by_count":31,"area":"rag"},{"id":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2501.16214","title":"Provence: efficient and robust context pruning for retrieval-augmented generation","created":"2025-01-27","cited_by_count":25,"area":"rag"},{"id":"2310.07815","title":"Language Models As Semantic Indexers","created":"2023-10-11","cited_by_count":20,"area":null},{"id":"2408.12503","title":"The Russian-focused embedders' exploration: ruMTEB benchmark and Russian embedding model design","created":"2024-08-22","cited_by_count":20,"area":null},{"id":"2404.14600","title":"Planning Ahead in Generative Retrieval: Guiding Autoregressive Generation through Simultaneous Decoding","created":"2024-04-22","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":"2501.13742","title":"An Empirical Study of Retrieval-Augmented Code Generation: Challenges and Opportunities","created":"2025-01-23","cited_by_count":18,"area":"rag"},{"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":"2503.05037","title":"Collapse of Dense Retrievers: Short, Early, and Literal Biases Outranking Factual Evidence","created":"2025-03-06","cited_by_count":16,"area":"rag"},{"id":"2402.11573","title":"BGE Landmark Embedding: A Chunking-Free Embedding Method For Retrieval Augmented Long-Context Large Language Models","created":"2024-02-18","cited_by_count":15,"area":"rag"},{"id":"2502.07555","title":"O1 Embedder: Let Retrievers Think Before Action","created":"2025-02-11","cited_by_count":15,"area":"lr"},{"id":"2502.11401","title":"Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment","created":"2025-02-17","cited_by_count":14,"area":null},{"id":"2305.02564","title":"RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2023-05-04","cited_by_count":13,"area":null},{"id":"2404.04163","title":"Dwell in the Beginning: How Language Models Embed Long Documents for Dense Retrieval","created":"2024-04-05","cited_by_count":13,"area":null},{"id":"2402.11035","title":"Dense Passage Retrieval: Is it Retrieving?","created":"2024-02-16","cited_by_count":12,"area":"rag"},{"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":"2502.05878","title":"Retrieval-augmented Large Language Models for Financial Time Series Forecasting","created":"2025-02-09","cited_by_count":12,"area":"rag"},{"id":"2504.01818","title":"Efficient Constant-Space Multi-Vector Retrieval","created":"2025-04-02","cited_by_count":12,"area":null},{"id":"2305.07402","title":"Synergistic Interplay between Search and Large Language Models for Information Retrieval","created":"2023-05-12","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":"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":"2305.13915","title":"DAPR: A Benchmark on Document-Aware Passage Retrieval","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2402.12784","title":"Understanding and Mitigating the Threat of Vec2Text to Dense Retrieval Systems","created":"2024-02-20","cited_by_count":9,"area":null},{"id":"2510.14321","title":"Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm","created":"2025-10-16","cited_by_count":9,"area":"lr"},{"id":"2411.04403","title":"Towards Competitive Search Relevance For Inference-Free Learned Sparse Retrievers","created":"2024-11-07","cited_by_count":8,"area":"distill"},{"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":"2304.10195","title":"CoT-MoTE: Exploring ConTextual Masked Auto-Encoder Pre-training with Mixture-of-Textual-Experts for Passage Retrieval","created":"2023-04-20","cited_by_count":7,"area":null},{"id":"2307.16779","title":"Lexically-Accelerated Dense Retrieval","created":"2023-07-31","cited_by_count":7,"area":null},{"id":"2410.15801","title":"Improve Dense Passage Retrieval with Entailment Tuning","created":"2024-10-21","cited_by_count":7,"area":"rag"},{"id":"2502.05364","title":"Hypencoder: Hypernetworks for Information Retrieval","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2504.04405","title":"Universal Item Tokenization for Transferable Generative Recommendation","created":"2025-04-06","cited_by_count":7,"area":null},{"id":"2405.10725","title":"INDUS: Effective and Efficient Language Models for Scientific Applications","created":"2024-05-17","cited_by_count":6,"area":null},{"id":"2409.15699","title":"Lighter And Better: Towards Flexible Context Adaptation For Retrieval Augmented Generation","created":"2024-09-24","cited_by_count":6,"area":"rag"},{"id":"2410.12842","title":"A Two-Model Approach for Humour Style Recognition","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2509.03020","title":"Training LLMs to be Better Text Embedders through Bidirectional Reconstruction","created":"2025-09-03","cited_by_count":6,"area":null},{"id":"2404.15103","title":"Multi-view Content-aware Indexing for Long Document Retrieval","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2410.20163","title":"UniHGKR: Unified Instruction-aware Heterogeneous Knowledge Retrievers","created":"2024-10-26","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":"2504.05220","title":"Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation","created":"2025-04-07","cited_by_count":5,"area":"rag"},{"id":"2212.09114","title":"CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion","created":"2022-12-18","cited_by_count":4,"area":null},{"id":"2212.10192","title":"Adam: Dense Retrieval Distillation with Adaptive Dark Examples","created":"2022-12-20","cited_by_count":4,"area":"distill"},{"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":"2406.01197","title":"A Survey of Generative Information Retrieval","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2406.19892","title":"Automatic register identification for the open web using multilingual deep learning","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2409.12737","title":"MEXMA: Token-level objectives improve sentence representations","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2410.13179","title":"EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2412.00359","title":"Does Self-Attention Need Separate Weights in Transformers?","created":"2024-11-30","cited_by_count":4,"area":null},{"id":"2305.13197","title":"Challenging Decoder helps in Masked Auto-Encoder Pre-training for Dense Passage Retrieval","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2311.01666","title":"Plot Retrieval as an Assessment of Abstract Semantic Association","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2311.05472","title":"Text Representation Distillation via Information Bottleneck Principle","created":"2023-11-09","cited_by_count":3,"area":null},{"id":"2311.13921","title":"Some Like It Small: Czech Semantic Embedding Models for Industry Applications","created":"2023-11-23","cited_by_count":3,"area":null},{"id":"2401.11248","title":"Drop your Decoder: Pre-training with Bag-of-Word Prediction for Dense Passage Retrieval","created":"2024-01-20","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":"2502.06252","title":"CliniQ: A Multi-faceted Benchmark for Electronic Health Record Retrieval with Semantic Match Assessment","created":"2025-02-10","cited_by_count":3,"area":null},{"id":"2506.16552","title":"Revela: Dense Retriever Learning via Language Modeling","created":"2025-06-19","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":"2210.05521","title":"Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2211.08769","title":"RetroMAE v2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models","created":"2022-11-16","cited_by_count":2,"area":null},{"id":"2306.04357","title":"Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems","created":"2023-06-07","cited_by_count":2,"area":null},{"id":"2308.15711","title":"Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection","created":"2023-08-30","cited_by_count":2,"area":null},{"id":"2405.13084","title":"The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)","created":"2024-05-21","cited_by_count":2,"area":"rag"},{"id":"2409.07737","title":"Ruri: Japanese General Text Embeddings","created":"2024-09-12","cited_by_count":2,"area":null},{"id":"2503.14800","title":"Long Context Modeling with Ranked Memory-Augmented Retrieval","created":"2025-03-19","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":"2506.00980","title":"LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World","created":"2025-06-01","cited_by_count":2,"area":null},{"id":"2510.16540","title":"Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions","created":"2025-10-18","cited_by_count":2,"area":"lr"},{"id":"2404.16248","title":"URL: Universal Referential Knowledge Linking via Task-instructed Representation Compression","created":"2024-04-24","cited_by_count":1,"area":null},{"id":"2505.12260","title":"LightRetriever: A LLM-based Text Retrieval Architecture with Extremely Faster Query Inference","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2506.00049","title":"Rethinking Hybrid Retrieval: When Small Embeddings and LLM Re-ranking Beat Bigger Models","created":"2025-05-28","cited_by_count":1,"area":"lr"},{"id":"2506.06335","title":"FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models","created":"2025-05-31","cited_by_count":1,"area":null},{"id":"2507.03958","title":"A Comparative Study of Specialized LLMs as Dense Retrievers","created":"2025-07-05","cited_by_count":1,"area":"mllm"},{"id":"2512.23065","title":"TabiBERT: A Large-Scale ModernBERT Foundation Model and A Unified Benchmark for Turkish","created":"2025-12-28","cited_by_count":1,"area":null},{"id":"2601.00543","title":"ECR: Manifold-Guided Semantic Cues for Compact Language Models","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2601.21525","title":"LMK > CLS: Landmark Pooling for Dense Embeddings","created":"2026-01-29","cited_by_count":1,"area":null},{"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":"2602.12727","title":"Training Dense Retrievers with Multiple Positive Passages","created":"2026-02-13","cited_by_count":1,"area":"rag"},{"id":"2306.10056","title":"Generate to Understand for Representation","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2306.12857","title":"Efficient Partitioning Method of Large-Scale Public Safety Spatio-Temporal Data based on Information Loss Constraints","created":"2023-06-22","cited_by_count":0,"area":null},{"id":"2306.12859","title":"Reinforcement Federated Learning Method Based on Adaptive OPTICS Clustering","created":"2023-06-22","cited_by_count":0,"area":null},{"id":"2311.00300","title":"Entity Alignment Method of Science and Technology Patent based on Graph Convolution Network and Information Fusion","created":"2023-11-01","cited_by_count":0,"area":null},{"id":"2311.00314","title":"Federated Topic Model and Model Pruning Based on Variational Autoencoder","created":"2023-11-01","cited_by_count":0,"area":null}],"next_cursor":"100"}