{"total":23,"rows":[{"id":"2402.18766","title":"Advancing Generative AI for Portuguese with Open Decoder Gerv\\'asio PT*","created":"2024-02-29","cited_by_count":19,"area":null},{"id":"2402.12969","title":"Gl\\'orIA -- A Generative and Open Large Language Model for Portuguese","created":"2024-02-20","cited_by_count":16,"area":null},{"id":"2401.16640","title":"TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese","created":"2024-01-30","cited_by_count":13,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2403.01897","title":"Fostering the Ecosystem of Open Neural Encoders for Portuguese with Albertina PT* Family","created":"2024-03-04","cited_by_count":8,"area":null},{"id":"2406.10806","title":"ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language","created":"2024-06-16","cited_by_count":8,"area":null},{"id":"2509.08824","title":"Building High-Quality Datasets for Portuguese LLMs: From Common Crawl Snapshots to Industrial-Grade Corpora","created":"2025-09-10","cited_by_count":7,"area":null},{"id":"2404.05333","title":"PORTULAN ExtraGLUE Datasets and Models: Kick-starting a Benchmark for the Neural Processing of Portuguese","created":"2024-04-08","cited_by_count":5,"area":null},{"id":"2407.19527","title":"Open Sentence Embeddings for Portuguese with the Serafim PT* encoders family","created":"2024-07-28","cited_by_count":4,"area":null},{"id":"2512.12770","title":"Curi\\'o-Edu 7B: Examining Data Selection Impacts in LLM Continued Pretraining","created":"2025-12-14","cited_by_count":4,"area":null},{"id":"2309.16844","title":"DeBERTinha: A Multistep Approach to Adapt DebertaV3 XSmall for Brazilian Portuguese Natural Language Processing Task","created":"2023-09-28","cited_by_count":2,"area":null},{"id":"2402.19204","title":"PeLLE: Encoder-based language models for Brazilian Portuguese based on open data","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2405.00536","title":"A Legal Framework for Natural Language Processing Model Training in Portugal","created":"2024-05-01","cited_by_count":1,"area":null},{"id":"2605.00086","title":"NorBERTo: A ModernBERT Model Trained for Portuguese with 331 Billion Tokens Corpus","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2402.14972","title":"MultiLS: A Multi-task Lexical Simplification Framework","created":"2024-02-22","cited_by_count":0,"area":null},{"id":"2506.15598","title":"From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns","created":"2025-06-18","cited_by_count":0,"area":null},{"id":"2508.10911","title":"Uncovering Latent Connections in Indigenous Heritage: Semantic Pipelines for Cultural Preservation in Brazil","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2602.12137","title":"CitiLink-Minutes: A Multilayer Annotated Dataset of Municipal Meeting Minutes","created":"2026-02-12","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":"2604.18878","title":"LegalBench-BR: A Benchmark for Evaluating Large Language Models on Brazilian Legal Decision Classification","created":"2026-04-20","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":"2606.28999","title":"BERTomelo: Your Portuguese Encoder Best Friend","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2608.18138","title":"Language Models for Portuguese: A Systematic Mapping Study","created":"2026-08-03","cited_by_count":0,"area":null}],"next_cursor":null}