{"total":30,"rows":[{"id":"2508.21038","title":"On the Theoretical Limitations of Embedding-Based Retrieval","created":"2025-08-28","cited_by_count":104,"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":"2508.07662","title":"GLiClass: Generalist Lightweight Model for Sequence Classification Tasks","created":"2025-08-11","cited_by_count":15,"area":null},{"id":"2602.18487","title":"The Million-Label NER: Breaking Scale Barriers with GLiNER bi-encoder","created":"2026-02-11","cited_by_count":5,"area":null},{"id":"2510.12327","title":"Simple Projection Variants Improve ColBERT Performance","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2602.05062","title":"Scaling Laws for Embedding Dimension in Information Retrieval","created":"2026-02-04","cited_by_count":2,"area":null},{"id":"2511.16528","title":"TurkColBERT: A Benchmark of Dense and Late-Interaction Models for Turkish Information Retrieval","created":"2025-11-20","cited_by_count":1,"area":null},{"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":"2603.15130","title":"Indirect Question Answering in English, German and Bavarian: A Challenging Task for High- and Low-Resource Languages Alike","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2605.06903","title":"MELD: Multi-Task Equilibrated Learning Detector for AI-Generated Text","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.12438","title":"A Causal Language Modeling Detour Improves Encoder Continued Pretraining","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2507.23386","title":"Causal2Vec: Improving Decoder-only LLMs as Embedding Models through a Contextual Token","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2512.03903","title":"BERnaT: Basque Encoders for Representing Natural Textual Diversity","created":"2025-12-03","cited_by_count":0,"area":null},{"id":"2601.09648","title":"Creating a Hybrid Rule and Neural Network Based Semantic Tagger using Silver Standard Data: the PyMUSAS framework for Multilingual Semantic Annotation","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2602.04605","title":"RexBERT: Context Specialized Bidirectional Encoders for E-commerce","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2602.21379","title":"MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.18676","title":"MANAR: Memory-augmented Attention with Navigational Abstract Conceptual Representation","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2603.24222","title":"Variation is the Norm: Embracing Sociolinguistics in NLP","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.29497","title":"Distilling Human-Aligned Privacy Sensitivity Assessment from Large Language Models","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.17976","title":"ltzGLUE: Luxembourgish General Language Understanding Evaluation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.21870","title":"Locating acts of mechanistic reasoning in student team conversations with mechanistic machine learning","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.02504","title":"A multilingual hallucination benchmark: MultiWikiQHalluA","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.18811","title":"Rescaling MLM-Head for Neural Sparse Retrieval","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.21356","title":"SOHET: Sequence Of Heterogeneous Events Transformer with Self-Supervised Pre-Training","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.22722","title":"moBERTo: A Modern Encoder for Portuguese via Continued Pretraining of ModernBERT","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2607.09749","title":"MorphologyFM: A Foundation Model for Morphology-Aware Representation Learning from ECG and Pulse Oximetry Waveforms","created":"2026-07-03","cited_by_count":0,"area":null},{"id":"2609.34986","title":"N\\\"urnberg NLP at ChildSafeAds 2026: Structurally Dissimilar Voter Ensembles under Four Levels of Data Access","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.05817","title":"Nash Equilibrium Text: A Game-Theoretic Decoding Framework for Text Generation","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.15028","title":"UltraBERT: Beyond the Limit of BERT Pre-Training","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.17658","title":"Worth Their Weights? Evaluating Generative Models for Discourse Parsing","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}