{"total":40,"rows":[{"id":"2511.01066","title":"HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models","created":"2025-11-02","cited_by_count":7,"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":"2604.02045","title":"BidirLM: From Text to Omnimodal Bidirectional Encoders by Adapting and Composing Causal LLMs","created":"2026-04-02","cited_by_count":5,"area":null},{"id":"2601.07533","title":"Loci Similes: A Benchmark for Extracting Intertextualities in Latin Literature","created":"2026-01-12","cited_by_count":3,"area":null},{"id":"2605.23033","title":"Uncovering the Latent Potential of Deep Intermediate Representations","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2509.21269","title":"LLMTrace: A Corpus for Classification and Fine-Grained Localization of AI-Written Text","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2510.05144","title":"SynCED-EnDe 2025: A Synthetic and Curated English - German Dataset for Critical Error Detection in Machine Translation","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2601.16018","title":"Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain","created":"2026-01-22","cited_by_count":2,"area":null},{"id":"2608.25768","title":"MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculum","created":"2026-08-26","cited_by_count":2,"area":null},{"id":"2510.20386","title":"NeoDictaBERT: Pushing the Frontier of BERT models for Hebrew","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2510.21372","title":"HalleluBERT: Let Every Token That Has Meaning Bear Its Weight","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2511.09748","title":"How Small Can You Go? Compact Language Models for On-Device Critical Error Detection in Machine Translation","created":"2025-11-12","cited_by_count":1,"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":"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":"2603.12191","title":"Long-Context Encoder Models for Polish Language Understanding","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.25360","title":"Learning to Route Languages for Multilingual Policy Optimization","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2606.30312","title":"DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal information","created":"2026-06-29","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":"2609.30706","title":"LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2511.05135","title":"ManufactuBERT: Efficient Continual Pretraining for Manufacturing","created":"2025-11-07","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":"2602.11444","title":"Towards Reliable Machine Translation: Scaling LLMs for Critical Error Detection and Safety","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.15716","title":"Rethinking Metrics for Lexical Semantic Change Detection","created":"2026-02-17","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":"2603.03884","title":"CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents","created":"2026-03-04","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":"2605.14257","title":"Sakura at BEA 2026 Shared Task 1: What Makes Vocabulary Difficult?","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.05444","title":"Multilingual Coreference Resolution via Cycle-Consistent Machine Translation","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.14626","title":"Characterizing Cultural Localization in AI-Generated Stories","created":"2026-06-12","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":"2608.26344","title":"MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for Turkish","created":"2026-08-26","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":"2609.36965","title":"Chinese-Jev: Bringing System One Model to Chinese-Language Tasks","created":"2026-09-29","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":"2610.11585","title":"Adapting English Quality Classifiers for Multilingual LLM Pretraining Data Selection","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.14112","title":"Does System One Transfer? Calibrated Typed-Decision Models, Label Budgets, and Translation for Indonesian Regional Languages","created":"2026-10-09","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":"2610.20263","title":"Anuvani-LID: Robust and Calibrated Spoken Language Identification for Indian Languages","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}