{"total":54,"rows":[{"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":"2109.11635","title":"Revisiting the Uniform Information Density Hypothesis","created":"2021-09-23","cited_by_count":68,"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":"2103.10685","title":"Controllable Generation from Pre-trained Language Models via Inverse Prompting","created":"2021-03-19","cited_by_count":29,"area":null},{"id":"2301.09626","title":"Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning","created":"2023-01-23","cited_by_count":26,"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":"2406.14670","title":"Exploring Design Choices for Building Language-Specific LLMs","created":"2024-06-20","cited_by_count":22,"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":"2309.04679","title":"Embedding structure matters: Comparing methods to adapt multilingual vocabularies to new languages","created":"2023-09-09","cited_by_count":16,"area":null},{"id":"2312.11779","title":"Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies","created":"2023-12-19","cited_by_count":16,"area":null},{"id":"2109.07348","title":"Cross-lingual Transfer of Monolingual Models","created":"2021-09-15","cited_by_count":14,"area":null},{"id":"2310.20384","title":"Do large language models solve verbal analogies like children do?","created":"2023-10-31","cited_by_count":13,"area":null},{"id":"2411.06096","title":"A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese","created":"2024-11-09","cited_by_count":13,"area":null},{"id":"2105.02855","title":"Adapting Monolingual Models: Data can be Scarce when Language Similarity is High","created":"2021-05-06","cited_by_count":12,"area":null},{"id":"2109.04556","title":"Subword Mapping and Anchoring across Languages","created":"2021-09-09","cited_by_count":12,"area":null},{"id":"2310.15004","title":"When Language Models Fall in Love: Animacy Processing in Transformer Language Models","created":"2023-10-23","cited_by_count":12,"area":null},{"id":"2412.06484","title":"Small Languages, Big Models: A Study of Continual Training on Languages of Norway","created":"2024-12-09","cited_by_count":12,"area":null},{"id":"2310.03477","title":"Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2601.07220","title":"The Roots of Performance Disparity in Multilingual Language Models: Intrinsic Modeling Difficulty or Design Choices?","created":"2026-01-12","cited_by_count":11,"area":null},{"id":"2312.01314","title":"NLEBench+NorGLM: A Comprehensive Empirical Analysis and Benchmark Dataset for Generative Language Models in Norwegian","created":"2023-12-03","cited_by_count":9,"area":null},{"id":"2405.12413","title":"Targeted Multilingual Adaptation for Low-resource Language Families","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2412.21140","title":"Facilitating large language model Russian adaptation with Learned Embedding Propagation","created":"2024-12-30","cited_by_count":8,"area":null},{"id":"2111.06336","title":"Character-level HyperNetworks for Hate Speech Detection","created":"2021-11-11","cited_by_count":7,"area":null},{"id":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","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":"2312.02598","title":"Impact of Tokenization on LLaMa Russian Adaptation","created":"2023-12-05","cited_by_count":5,"area":null},{"id":"2406.11418","title":"BAMBINO-LM: (Bilingual-)Human-Inspired Continual Pretraining of BabyLM","created":"2024-06-17","cited_by_count":5,"area":null},{"id":"2407.12869","title":"Bilingual Adaptation of Monolingual Foundation Models","created":"2024-07-13","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":"2412.20357","title":"HindiLLM: Large Language Model for Hindi","created":"2024-12-29","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":"2101.01628","title":"Local Translation Services for Neglected Languages","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2407.12790","title":"GPT Czech Poet: Generation of Czech Poetic Strophes with Language Models","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2408.15793","title":"Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2504.17025","title":"Optimizing LLMs for Italian: Reducing Token Fertility and Enhancing Efficiency Through Vocabulary Adaptation","created":"2025-04-23","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":"2208.14554","title":"Do language models make human-like predictions about the coreferents of Italian anaphoric zero pronouns?","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2210.06928","title":"Sentence Ambiguity, Grammaticality and Complexity Probes","created":"2022-10-13","cited_by_count":1,"area":null},{"id":"2210.11618","title":"Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve","created":"2022-10-20","cited_by_count":1,"area":null},{"id":"2403.06018","title":"Few-Shot Cross-Lingual Transfer for Prompting Large Language Models in Low-Resource Languages","created":"2024-03-09","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":"2205.11616","title":"Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment","created":"2022-05-23","cited_by_count":0,"area":null},{"id":"2209.06422","title":"Language Chameleon: Transformation analysis between languages using Cross-lingual Post-training based on Pre-trained language models","created":"2022-09-14","cited_by_count":0,"area":null},{"id":"2506.19187","title":"Prompt, Translate, Fine-Tune, Re-Initialize, or Instruction-Tune? Adapting LLMs for In-Context Learning in Low-Resource Languages","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2510.23198","title":"PTPP-Aware Adaptation Scaling Laws: Predicting Domain-Adaptation Performance at Unseen Pre-Training Budgets","created":"2025-10-27","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},{"id":"2603.22629","title":"LGSE: Lexically Grounded Subword Embedding Initialization for Low-Resource Language Adaptation","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2606.06738","title":"Modular Monolingual Adaptation using Pretrained Language Models","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.15868","title":"David vs. Goliath in Next Activity Prediction: Argmax vs. LSTM, Transformer, and LLM","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.21203","title":"When Context Misleads: Surprisal, Energy and Attention Entropy as Metrics of Coherence Illusions in LLMs","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2609.02651","title":"WinoQueer-NL: Assessing Bias in Dutch Language Models toward LGBTQ+ Identities","created":"2026-09-02","cited_by_count":0,"area":null}],"next_cursor":null}