{"total":29,"rows":[{"id":"2204.06487","title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","created":"2022-04-13","cited_by_count":149,"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":"2305.15020","title":"An Efficient Multilingual Language Model Compression through Vocabulary Trimming","created":"2023-05-24","cited_by_count":20,"area":null},{"id":"2109.12346","title":"DziriBERT: a Pre-trained Language Model for the Algerian Dialect","created":"2021-09-25","cited_by_count":18,"area":null},{"id":"2304.00906","title":"ScandEval: A Benchmark for Scandinavian Natural Language Processing","created":"2023-04-03","cited_by_count":16,"area":null},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2105.09052","title":"Methods for Detoxification of Texts for the Russian Language","created":"2021-05-19","cited_by_count":13,"area":null},{"id":"2204.09391","title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2203.15996","title":"TextPruner: A Model Pruning Toolkit for Pre-Trained Language Models","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2207.09150","title":"On the Usability of Transformers-based models for a French Question-Answering task","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2401.10660","title":"Accelerating Multilingual Language Model for Excessively Tokenized Languages","created":"2024-01-19","cited_by_count":8,"area":null},{"id":"2107.05684","title":"Accenture at CheckThat! 2021: Interesting claim identification and ranking with contextually sensitive lexical training data augmentation","created":"2021-07-12","cited_by_count":6,"area":null},{"id":"2109.08607","title":"The futility of STILTs for the classification of lexical borrowings in Spanish","created":"2021-09-17","cited_by_count":6,"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":"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":"2510.08599","title":"BaldWhisper: Faster Whisper with Head Shearing and Layer Merging","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2207.09152","title":"Benchmarking Transformers-based models on French Spoken Language Understanding tasks","created":"2022-07-19","cited_by_count":3,"area":null},{"id":"2311.09709","title":"The Ups and Downs of Large Language Model Inference with Vocabulary Trimming by Language Heuristics","created":"2023-11-16","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":"2501.02631","title":"Prune or Retrain: Optimizing the Vocabulary of Multilingual Models for Estonian","created":"2025-01-05","cited_by_count":3,"area":null},{"id":"2106.01735","title":"Auto-tagging of Short Conversational Sentences using Transformer Methods","created":"2021-06-03","cited_by_count":2,"area":null},{"id":"2309.08708","title":"Vocabulary-level Memory Efficiency for Language Model Fine-tuning","created":"2023-09-15","cited_by_count":2,"area":null},{"id":"2310.02790","title":"Low Resource Summarization using Pre-trained Language Models","created":"2023-10-04","cited_by_count":2,"area":null},{"id":"2205.14981","title":"ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2509.15380","title":"Efficient and Versatile Model for Multilingual Information Retrieval of Islamic Text: Development and Deployment in Real-World Scenarios","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2302.00856","title":"idT5: Indonesian Version of Multilingual T5 Transformer","created":"2023-02-02","cited_by_count":0,"area":null},{"id":"2305.14070","title":"Assessing Linguistic Generalisation in Language Models: A Dataset for Brazilian Portuguese","created":"2023-05-23","cited_by_count":0,"area":null},{"id":"2505.23297","title":"EmoBench-UA: A Benchmark Dataset for Emotion Detection in Ukrainian","created":"2025-05-29","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}