{"total":33,"rows":[{"id":"2404.17790","title":"Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities","created":"2024-04-27","cited_by_count":111,"area":null},{"id":"2403.18421","title":"BioMedLM: A 2.7B Parameter Language Model Trained On Biomedical Text","created":"2024-03-27","cited_by_count":86,"area":null},{"id":"2305.16876","title":"CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models","created":"2023-05-23","cited_by_count":26,"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":"2211.03154","title":"On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey","created":"2022-11-06","cited_by_count":23,"area":null},{"id":"2310.05317","title":"Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond","created":"2023-10-09","cited_by_count":23,"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":"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":"2405.09913","title":"TransMI: A Framework to Create Strong Baselines from Multilingual Pretrained Language Models for Transliterated Data","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2507.12720","title":"FLEXITOKENS: Flexible Tokenization for Evolving Language Models","created":"2025-07-17","cited_by_count":8,"area":null},{"id":"2405.01883","title":"DALLMi: Domain Adaption for LLM-based Multi-label Classifier","created":"2024-05-03","cited_by_count":7,"area":null},{"id":"2302.02080","title":"Improving Prediction Backward-Compatiblility in NLP Model Upgrade with Gated Fusion","created":"2023-02-04","cited_by_count":6,"area":null},{"id":"2406.09330","title":"Learning from Natural Language Explanations for Generalizable Entity Matching","created":"2024-06-13","cited_by_count":6,"area":null},{"id":"2408.06345","title":"Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review","created":"2024-07-23","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":"2307.00963","title":"Challenges in Domain-Specific Abstractive Summarization and How to Overcome them","created":"2023-07-03","cited_by_count":5,"area":null},{"id":"2501.10175","title":"Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval","created":"2025-01-17","cited_by_count":4,"area":null},{"id":"2311.00408","title":"AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification","created":"2023-11-01","cited_by_count":3,"area":null},{"id":"2411.06151","title":"Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rust","created":"2024-11-09","cited_by_count":3,"area":null},{"id":"2412.02228","title":"BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2601.03181","title":"Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey","created":"2026-01-06","cited_by_count":3,"area":null},{"id":"2601.21665","title":"AdaptBPE: From General Purpose to Specialized Tokenizers","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2308.08625","title":"BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognition","created":"2023-08-16","cited_by_count":2,"area":null},{"id":"2209.12943","title":"Towards Simple and Efficient Task-Adaptive Pre-training for Text Classification","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2403.13681","title":"Ayn: A Tiny yet Competitive Indian Legal Language Model Pretrained from Scratch","created":"2024-03-20","cited_by_count":1,"area":null},{"id":"2410.03258","title":"Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2501.02842","title":"Foundations of GenIR","created":"2025-01-06","cited_by_count":1,"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":"2405.00307","title":"Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2510.16797","title":"MOSAIC: Masked Objective with Selective Adaptation for In-domain Contrastive Learning","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2602.24174","title":"Task-Centric Acceleration of Small-Language Models","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2604.06171","title":"LLM-Augmented Knowledge Base Construction For Root Cause Analysis","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2605.17379","title":"Learning Faster with Better Tokens: Parameter-Efficient Vocabulary Adaptation for Specialized Text Summarization","created":"2026-05-17","cited_by_count":0,"area":null}],"next_cursor":null}