{"total":42,"rows":[{"id":"2406.17557","title":"The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale","created":"2024-06-25","cited_by_count":1160,"area":null},{"id":"2412.02595","title":"Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining Dataset","created":"2024-12-03","cited_by_count":160,"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":"2504.16980","title":"Safety Pretraining: Toward the Next Generation of Safe AI","created":"2025-04-23","cited_by_count":43,"area":null},{"id":"2409.11136","title":"Promptriever: Instruction-Trained Retrievers Can Be Prompted Like Language Models","created":"2024-09-17","cited_by_count":40,"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":"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":"2505.07849","title":"SweRank: Software Issue Localization with Code Ranking","created":"2025-05-07","cited_by_count":20,"area":null},{"id":"2407.12929","title":"The 2024 Foundation Model Transparency Index","created":"2024-07-17","cited_by_count":19,"area":null},{"id":"2409.07691","title":"Enhancing Q&A Text Retrieval with Ranking Models: Benchmarking, fine-tuning and deploying Rerankers for RAG","created":"2024-09-12","cited_by_count":16,"area":null},{"id":"2407.20750","title":"JaColBERTv2.5: Optimising Multi-Vector Retrievers to Create State-of-the-Art Japanese Retrievers with Constrained Resources","created":"2024-07-30","cited_by_count":15,"area":null},{"id":"2501.03545","title":"Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation","created":"2025-01-07","cited_by_count":15,"area":null},{"id":"2410.08102","title":"Efficient Pretraining Data Selection for Language Models via Multi-Actor Collaboration","created":"2024-10-10","cited_by_count":10,"area":null},{"id":"2411.06638","title":"Model Editing for LLMs4Code: How Far are We?","created":"2024-11-11","cited_by_count":10,"area":null},{"id":"2507.05675","title":"MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos","created":"2025-07-08","cited_by_count":9,"area":null},{"id":"2510.07249","title":"TalkCuts: A Large-Scale Dataset for Multi-Shot Human Speech Video Generation","created":"2025-10-08","cited_by_count":6,"area":null},{"id":"2607.27178","title":"DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search","created":"2026-07-29","cited_by_count":6,"area":null},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2511.22150","title":"From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures","created":"2025-11-27","cited_by_count":5,"area":null},{"id":"2512.24265","title":"Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning","created":"2025-12-30","cited_by_count":5,"area":null},{"id":"2504.06293","title":"Generative AI Enhanced Financial Risk Management Information Retrieval","created":"2025-04-04","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":"2510.00866","title":"Removing Noise, not Finding Gold: Quality Filtering for Large-Scale Pretraining","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2410.12989","title":"Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2507.11830","title":"Arctic Inference with Shift Parallelism: Fast and Efficient Open Source Inference System for Enterprise AI","created":"2025-07-16","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":"2510.15087","title":"DMRetriever: A Family of Models for Improved Text Retrieval in Disaster Management","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2602.17687","title":"IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2605.31142","title":"On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2509.11941","title":"How to Evaluate Medical AI","created":"2025-09-15","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},{"id":"2512.06042","title":"Auto-SPT: Automating Semantic Preserving Transformations for Code","created":"2025-12-05","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":"2605.12714","title":"Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2510.04626","title":"Compressed Concatenation of Small Embedding Models","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2510.16797","title":"MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2511.01090","title":"Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering","created":"2025-11-02","cited_by_count":0,"area":null},{"id":"2603.13972","title":"FLUX: Data Worth Training On","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.26180","title":"Evergreen: Efficient Claim Verification for Semantic Aggregates","created":"2026-04-28","cited_by_count":0,"area":null},{"id":"2606.12332","title":"Measuring Semantic Progress in Multi-turn Dialogue via Information Gain","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.13311","title":"Finding the Right Tables and Columns: A Benchmark and Corpus-Adaptive Embeddings for SQL Schema Retrieval","created":"2026-07-14","cited_by_count":0,"area":null}],"next_cursor":null}