{"total":34,"rows":[{"id":"2409.06857","title":"What is the Role of Small Models in the LLM Era: A Survey","created":"2024-09-10","cited_by_count":41,"area":null},{"id":"2503.19693","title":"AdaptiVocab: Enhancing LLM Efficiency in Focused Domains through Lightweight Vocabulary Adaptation","created":"2025-03-25","cited_by_count":15,"area":null},{"id":"2501.04473","title":"When LLMs Struggle: Reference-less Translation Evaluation for Low-resource Languages","created":"2025-01-08","cited_by_count":7,"area":null},{"id":"2509.11414","title":"Continually Adding New Languages to Multilingual Language Models","created":"2025-09-14","cited_by_count":7,"area":null},{"id":"2412.11704","title":"Adapting Chat Language Models Using Only Target Unlabeled Language Data","created":"2024-12-16","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":"2510.21954","title":"Model-Aware Tokenizer Transfer","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2410.05021","title":"DEPT: Decoupled Embeddings for Pre-training Language Models","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2509.12340","title":"MTEB-NL and E5-NL: Embedding Benchmark and Models for Dutch","created":"2025-09-15","cited_by_count":5,"area":null},{"id":"2505.09738","title":"Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning","created":"2025-05-14","cited_by_count":4,"area":null},{"id":"2601.21665","title":"AdaptBPE: From General Purpose to Specialized Tokenizers","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2411.00593","title":"Adapting Language Models via Token Translation","created":"2024-11-01","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":"2506.01535","title":"Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2508.03628","title":"LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay","created":"2025-08-05","cited_by_count":2,"area":null},{"id":"2510.12389","title":"Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2603.09982","title":"AraModernBERT: Transtokenized Initialization and Long-Context Encoder Modeling for Arabic","created":"2026-02-10","cited_by_count":2,"area":null},{"id":"2604.16656","title":"Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion","created":"2026-04-17","cited_by_count":2,"area":null},{"id":"2607.26831","title":"Language Models are not Equally Robust to Non-Canonical Tokenization across Languages","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2509.26124","title":"Vocabulary Customization for Efficient Domain-Specific LLM Deployment","created":"2025-09-30","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":"2502.19784","title":"NaijaNLP: A Survey of Nigerian Low-Resource Languages","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2507.07824","title":"Conditional Unigram Tokenization with Parallel Data","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2602.05599","title":"BhashaSetu: Cross-Lingual Knowledge Transfer from High-Resource to Extreme Low-Resource Languages","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2603.27859","title":"KazByte: Adapting Qwen models to Kazakh via Byte-level Adapter","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2603.29221","title":"SiPaKosa: A Comprehensive Corpus of Canonical and Classical Buddhist Texts in Sinhala and Pali","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.01800","title":"Multilinguality of Large Language Models From a Structural Perspective","created":"2026-06-01","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":"2607.09598","title":"Tokenizer Transplantation: Mitigating Autoregressive Collapse in Edge-Efficient Bengali ASR","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2607.15209","title":"Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya","created":"2026-07-16","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":"2609.03350","title":"From Zero to Hero: An Open LLM Ecosystem for Armenian","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.20832","title":"TatBLiMP: A Benchmark of Linguistic Minimal Pairs for Tatar","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}