{"total":36,"rows":[{"id":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146,"area":null},{"id":"2204.08110","title":"Language Contamination Helps Explain the Cross-lingual Capabilities of English Pretrained Models","created":"2022-04-17","cited_by_count":92,"area":null},{"id":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89,"area":null},{"id":"2308.04948","title":"Extrapolating Large Language Models to Non-English by Aligning Languages","created":"2023-08-09","cited_by_count":69,"area":null},{"id":"2503.13423","title":"SuperBPE: Space Travel for Language Models","created":"2025-03-17","cited_by_count":63,"area":null},{"id":"2311.08849","title":"OFA: A Framework of Initializing Unseen Subword Embeddings for Efficient Large-scale Multilingual Continued Pretraining","created":"2023-11-15","cited_by_count":37,"area":null},{"id":"2405.07883","title":"Zero-Shot Tokenizer Transfer","created":"2024-05-13","cited_by_count":31,"area":null},{"id":"2211.06993","title":"GreenPLM: Cross-Lingual Transfer of Monolingual Pre-Trained Language Models at Almost No Cost","created":"2022-11-13","cited_by_count":24,"area":null},{"id":"2212.10503","title":"Mini-Model Adaptation: Efficiently Extending Pretrained Models to New Languages via Aligned Shallow Training","created":"2022-12-20","cited_by_count":24,"area":null},{"id":"2407.05841","title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models","created":"2024-07-08","cited_by_count":20,"area":null},{"id":"2402.10712","title":"An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Language Model Inference","created":"2024-02-16","cited_by_count":18,"area":null},{"id":"2109.04556","title":"Subword Mapping and Anchoring across Languages","created":"2021-09-09","cited_by_count":12,"area":null},{"id":"2506.03523","title":"TokAlign: Efficient Vocabulary Adaptation via Token Alignment","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2202.12312","title":"Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies","created":"2022-02-24","cited_by_count":9,"area":null},{"id":"2410.09644","title":"Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?","created":"2024-10-12","cited_by_count":9,"area":null},{"id":"2512.15586","title":"Bolmo: Byteifying the Next Generation of Language Models","created":"2025-12-17","cited_by_count":9,"area":null},{"id":"2502.12598","title":"Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion","created":"2025-02-18","cited_by_count":8,"area":null},{"id":"2506.14123","title":"Sampling from Your Language Model One Byte at a Time","created":"2025-06-17","cited_by_count":7,"area":null},{"id":"2306.01709","title":"Distilling Efficient Language-Specific Models for Cross-Lingual Transfer","created":"2023-06-02","cited_by_count":6,"area":null},{"id":"2505.20133","title":"Token Distillation: Attention-aware Input Embeddings For New Tokens","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2403.11130","title":"Exploring Tokenization Strategies and Vocabulary Sizes for Enhanced Arabic Language Models","created":"2024-03-17","cited_by_count":5,"area":null},{"id":"2410.04335","title":"ReTok: Replacing Tokenizer to Enhance Representation Efficiency in Large Language Model","created":"2024-10-06","cited_by_count":5,"area":null},{"id":"2505.02550","title":"Bielik v3 Small: Technical Report","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2109.07140","title":"On the Universality of Deep Contextual Language Models","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2107.12627","title":"Cross-lingual Transferring of Pre-trained Contextualized Language Models","created":"2021-07-27","cited_by_count":3,"area":null},{"id":"2504.21018","title":"HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization","created":"2025-04-21","cited_by_count":3,"area":null},{"id":"2104.08410","title":"Identifying the Limits of Cross-Domain Knowledge Transfer for Pretrained Models","created":"2021-04-17","cited_by_count":2,"area":null},{"id":"2505.10945","title":"Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transfer","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2505.14297","title":"Cross-Lingual Optimization for Language Transfer in Large Language Models","created":"2025-05-20","cited_by_count":2,"area":null},{"id":"2604.10799","title":"Advancing Polish Language Modeling through Tokenizer Optimization in the Bielik v3 7B and 11B Series","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2605.13429","title":"TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2103.09325","title":"Graph Convolutional Network for Swahili News Classification","created":"2021-03-16","cited_by_count":0,"area":null},{"id":"2305.14481","title":"FOCUS: Effective Embedding Initialization for Monolingual Specialization of Multilingual Models","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2402.14408","title":"Transferring BERT Capabilities from High-Resource to Low-Resource Languages Using Vocabulary Matching","created":"2024-02-22","cited_by_count":0,"area":null},{"id":"2404.00862","title":"Bailong: Bilingual Transfer Learning based on QLoRA and Zip-tie Embedding","created":"2024-04-01","cited_by_count":0,"area":null},{"id":"2602.09388","title":"Effective vocabulary expansion of multilingual language models for extremely low-resource languages","created":"2026-02-10","cited_by_count":0,"area":null}],"next_cursor":null}