{"total":24,"rows":[{"id":"2509.06888","title":"mmBERT: A Modern Multilingual Encoder with Annealed Language Learning","created":"2025-09-08","cited_by_count":45,"area":null},{"id":"2602.15547","title":"jina-embeddings-v5-text: Task-Targeted Embedding Distillation","created":"2026-02-17","cited_by_count":22,"area":null},{"id":"2505.08351","title":"Alignment Drift in CEFR-prompted LLMs for Interactive Spanish Tutoring","created":"2025-05-13","cited_by_count":7,"area":null},{"id":"2505.13136","title":"New Encoders for German Trained from Scratch: Comparing ModernGBERT with Converted LLM2Vec Models","created":"2025-05-19","cited_by_count":5,"area":null},{"id":"2510.21364","title":"SindBERT, the Sailor: Charting the Seas of Turkish NLP","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2508.20712","title":"Multi-Lingual Implicit Discourse Relation Recognition with Multi-Label Hierarchical Learning","created":"2025-08-28","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":"2601.05776","title":"One Script Instead of Hundreds? On Pretraining Romanized Encoder Language Models","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2601.09313","title":"Understanding or Memorizing? A Case Study of German Definite Articles in Language Models","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2603.12191","title":"Long-Context Encoder Models for Polish Language Understanding","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2606.13100","title":"LEDGER: A Long-Context Benchmark of Corporate Annual Reports for Grounded Financial Retrieval and Extraction","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2608.15323","title":"When Do Concepts Become Functionally Sufficient During Language-Model Training?","created":"2026-08-15","cited_by_count":1,"area":null},{"id":"2608.21023","title":"Scaling Unsupervised Word Alignment to Documents via Structural Constraints","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2512.22705","title":"GHaLIB: A Multilingual Framework for Hope Speech Detection in Low-Resource Languages","created":"2025-12-27","cited_by_count":0,"area":null},{"id":"2601.22885","title":"Leveraging LLMs For Turkish Skill Extraction","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2605.07622","title":"Is She Even Relevant? When BERT Ignores Explicit Gender Cues","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2605.15081","title":"ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.22079","title":"Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining","created":"2026-06-20","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":"2609.01379","title":"Polish ModernBERT: The Long and Short of Polish Language Understanding","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.14969","title":"Online Language Adaptive Sampling for Better Distributed Cross-lingual Gains","created":"2026-09-14","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":"2610.15028","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}