{"total":117,"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":"2508.04796","title":"Parity-Aware Byte-Pair Encoding: Improving Cross-lingual Fairness in Tokenization","created":"2025-08-06","cited_by_count":20,"area":null},{"id":"2603.11510","title":"Tiny Aya: Bridging Scale and Multilingual Depth","created":"2026-03-12","cited_by_count":15,"area":null},{"id":"2511.01380","title":"Confounding Factors in Relating Model Performance to Morphology","created":"2025-11-03","cited_by_count":14,"area":null},{"id":"2511.18903","title":"How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining","created":"2025-11-24","cited_by_count":14,"area":null},{"id":"2601.06395","title":"AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages","created":"2026-01-10","cited_by_count":12,"area":null},{"id":"2510.25947","title":"Revisiting Multilingual Data Mixtures in Language Model Pretraining","created":"2025-10-29","cited_by_count":10,"area":null},{"id":"2602.11151","title":"Diffusion-Pretrained Dense and Contextual Embeddings","created":"2026-02-11","cited_by_count":9,"area":null},{"id":"2510.03871","title":"Optimal Scaling Needs Optimal Norm","created":"2025-10-04","cited_by_count":8,"area":null},{"id":"2507.04569","title":"Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts","created":"2025-07-06","cited_by_count":7,"area":null},{"id":"2507.08924","title":"From KMMLU-Redux to KMMLU-Pro: A Professional Korean Benchmark Suite for LLM Evaluation","created":"2025-07-11","cited_by_count":6,"area":null},{"id":"2511.06531","title":"Ibom NLP: A Step Toward Inclusive Natural Language Processing for Nigeria's Minority Languages","created":"2025-11-09","cited_by_count":6,"area":null},{"id":"2601.11579","title":"Bielik 11B v3: Multilingual Large Language Model for European Languages","created":"2025-12-30","cited_by_count":6,"area":null},{"id":"2601.18026","title":"CommonLID: Re-evaluating State-of-the-Art Language Identification Performance on Web Data","created":"2026-01-25","cited_by_count":6,"area":null},{"id":"2602.12414","title":"propella-1: Multi-Property Document Annotation for LLM Data Curation at Scale","created":"2026-02-12","cited_by_count":6,"area":null},{"id":"2605.12715","title":"Scaling Laws for Mixture Pretraining Under Data Constraints","created":"2026-05-12","cited_by_count":6,"area":null},{"id":"2507.01785","title":"MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining","created":"2025-07-02","cited_by_count":5,"area":null},{"id":"2602.13139","title":"OpenLID-v3: Improving the Precision of Closely Related Language Identification -- An Experience Report","created":"2026-02-13","cited_by_count":5,"area":null},{"id":"2509.14493","title":"Translate, then Detect: Leveraging Machine Translation for Cross-Lingual Toxicity Classification","created":"2025-09-17","cited_by_count":4,"area":null},{"id":"2511.07464","title":"Motif 2 12.7B technical report","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2512.20757","title":"TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2605.01188","title":"Compute Optimal Tokenization","created":"2026-05-02","cited_by_count":4,"area":null},{"id":"2510.13996","title":"The German Commons - 154 Billion Tokens of Openly Licensed Text for German Language Models","created":"2025-10-15","cited_by_count":3,"area":null},{"id":"2512.00333","title":"IndicParam: Benchmark to evaluate LLMs on low-resource Indic Languages","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2512.13884","title":"FiNERweb: Datasets and Artifacts for Scalable Multilingual Named Entity Recognition","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2602.03484","title":"Preferences for Idiomatic Language are Acquired Slowly -- and Forgotten Quickly: A Case Study on Swedish","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.15210","title":"\\\"UberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset","created":"2026-02-16","cited_by_count":3,"area":null},{"id":"2603.17945","title":"ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws","created":"2026-03-18","cited_by_count":3,"area":null},{"id":"2606.07874","title":"Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2607.27183","title":"Pangram 4 Technical Report","created":"2026-07-29","cited_by_count":3,"area":null},{"id":"2511.02752","title":"AI Diffusion in Low Resource Language Countries","created":"2025-11-04","cited_by_count":2,"area":null},{"id":"2512.03989","title":"Teaching Old Tokenizers New Words: Efficient Tokenizer Adaptation for Pre-trained Models","created":"2025-12-03","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":"2602.00747","title":"Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2602.11089","title":"DataChef: Cooking Up Optimal Data Recipes for LLM Adaptation via Reinforcement Learning","created":"2026-02-11","cited_by_count":2,"area":null},{"id":"2603.08182","title":"TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2603.25489","title":"Translation Asymmetry in LLMs as a Data Augmentation Factor: A Case Study for 6 Romansh Language Varieties","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2605.27379","title":"Soro: A Lightweight Foundation Model and Chatbot for Tajik","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2608.18062","title":"TokEval: A Tokenizer Evaluation Suite","created":"2026-08-18","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":"2608.26449","title":"Vowel Signs Are Not Letters: A Pre-tokenization Ceiling on Multilingual Tokenizer Fertility","created":"2026-08-26","cited_by_count":2,"area":null},{"id":"2609.25081","title":"ufakzeka-1: Building and Evaluating a 151M-Parameter Turkish Language Model from Scratch","created":"2026-09-18","cited_by_count":2,"area":null},{"id":"2508.14913","title":"Bridging the Culture Gap: A Framework for LLM-Driven Socio-Cultural Localization of Math Word Problems in Low-Resource Languages","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2510.17001","title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2511.05560","title":"Sample-Efficient Language Modeling with Linear Attention and Lightweight Enhancements","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2512.18834","title":"Mix, MinHash, and Match: Cross-Source Agreement for Multilingual Pretraining Datasets","created":"2025-12-21","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":"2601.00364","title":"The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2602.02104","title":"Dicta-LM 3.0: Advancing The Frontier of Hebrew Sovereign LLMs","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2602.10657","title":"Benchmarks Are Not That Out of Distribution: Word Overlap Predicts Performance","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.00620","title":"QQ: A Language Metadata Toolkit for Multilingual NLP","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2603.01691","title":"Building a Strong Instruction Language Model for a Less-Resourced Language","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.02041","title":"EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2604.06210","title":"Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebook","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.18232","title":"SomaliWeb v1: A Quality-Filtered Somali Web Corpus with a Matched Tokenizer and a Public Language-Identification Benchmark","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.03773","title":"KletterMix: Climbing Toward High-Quality German Pretraining Data - The Full Report","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.28057","title":"MultiHashFormer: Hash-based Generative Language Models","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2607.15232","title":"In-Place Tokenizer Expansion for Pre-trained LLMs","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2607.20078","title":"RALS: Resources and Baselines for Romanian Automatic Lexical Simplification","created":"2026-07-22","cited_by_count":1,"area":null},{"id":"2608.25832","title":"Skill Issue: Are Skills Language-Invariant in LLMs?","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2508.09148","title":"Motif 2.6B Technical Report","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2509.05060","title":"Entropy2Vec: Crosslingual Language Modeling Entropy as End-to-End Learnable Language Representations","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2509.15556","title":"Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2510.13481","title":"Tahakom LLM Guidelines and Recipes: From Pre-training Data to an Arabic LLM","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.03270","title":"SCALE: Upscaled Continual Learning of Large Language Models","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2512.09701","title":"FineFreq: A Multilingual Character Frequency Dataset from Web-Scale Text","created":"2025-12-10","cited_by_count":0,"area":null},{"id":"2512.13330","title":"FIN-bench-v2: A Unified and Robust Benchmark Suite for Evaluating Finnish Large Language Models","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2601.09716","title":"Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2601.10804","title":"BYOL: Bring Your Own Language Into LLMs","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.11170","title":"The Growing Gains and Pains of Iterative Web Corpora Crawling: Insights from South Slavic CLASSLA-web 2.0 Corpora","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2601.13346","title":"AfroScope: A Framework for Studying the Linguistic Landscape of Africa","created":"2026-01-19","cited_by_count":0,"area":null},{"id":"2601.17664","title":"UrduLM: A Resource-Efficient Monolingual Urdu Language Model","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2601.17823","title":"DIETA: A Decoder-only transformer-based model for Italian-English machine TrAnslation","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2601.21587","title":"A Study of Crosslinguistic Influence in Language Models","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.08951","title":"How Should We Model the Probability of a Language?","created":"2026-02-09","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":"2603.03508","title":"Raising Bars, Not Parameters: LilMoo Compact Language Model for Hindi","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.29026","title":"On the limited utility of parallel data for learning shared multilingual representations","created":"2026-03-30","cited_by_count":0,"area":null},{"id":"2604.20549","title":"Toward Cross-Lingual Quality Classifiers for Multilingual Pretraining Data Selection","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.28075","title":"Repetition over Diversity: High-Signal Data Filtering for Sample-Efficient German Language Modeling","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.13225","title":"Mix, Don't Tune: Bilingual Pre-Training Outperforms Hyperparameter Search in Data-Constrained Settings","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.23885","title":"Multilingual Knowledge Transfer under Data Constraints via Lexical Interventions","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.25263","title":"Mimir: Large-scale Multilingual Concept Modeling","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2606.06088","title":"CHALIS: A Challenge Dataset for Language Identification in Difficult Scenarios","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.15044","title":"Equity with Efficiency: An Empirical Study of Tokenizers for Multilingual Large Language Models","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.21638","title":"Toward Open Weight Models Without Risks: Separating Public and Private Capabilities in LLMs","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":"2606.23566","title":"LangMAP: A Language-Adaptive Approach to Tokenization","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.00890","title":"MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.21445","title":"When Trivia Is Not Trivial: Everyday Knowledge Failures in Multilingual LLMs","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.22662","title":"CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2608.03089","title":"Scalable Frequency- and Length-Aware Subdocument Deduplication for Large Language Model Pretraining","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.15964","title":"LLMs Get Smarter from Targeted Synthetic Multilingual Data","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.25904","title":"One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.27658","title":"When Tokenizers Fail: Byte-Level Chunking for Zero-Shot Transfer to Low-Resource Languages","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.28622","title":"PUFFER: Incremental Fuzzy Deduplication for Continuously Evolving Corpora","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.30541","title":"Seeing the Unseen: Visual Similarity for Pixel Language Model Adaptation","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.01341","title":"Probing Factual Knowledge Transfer with Training Data Interventions","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.03350","title":"From Zero to Hero: An Open LLM Ecosystem for Armenian","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":"100"}