{"total":23,"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":"2110.07560","title":"Composable Sparse Fine-Tuning for Cross-Lingual Transfer","created":"2021-10-14","cited_by_count":144,"area":null},{"id":"2109.03646","title":"Sustainable Modular Debiasing of Language Models","created":"2021-09-08","cited_by_count":100,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2311.09344","title":"Language and Task Arithmetic with Parameter-Efficient Layers for Zero-Shot Summarization","created":"2023-11-15","cited_by_count":28,"area":null},{"id":"2305.14224","title":"mmT5: Modular Multilingual Pre-Training Solves Source Language Hallucinations","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2106.09063","title":"Specializing Multilingual Language Models: An Empirical Study","created":"2021-06-16","cited_by_count":21,"area":null},{"id":"2306.02767","title":"Cross-Lingual Transfer with Target Language-Ready Task Adapters","created":"2023-06-05","cited_by_count":15,"area":null},{"id":"2111.00667","title":"Unsupervised Domain Adaptation with Adapter","created":"2021-11-01","cited_by_count":14,"area":null},{"id":"2303.17683","title":"Fine-Tuning BERT with Character-Level Noise for Zero-Shot Transfer to Dialects and Closely-Related Languages","created":"2023-03-30","cited_by_count":9,"area":null},{"id":"2108.08103","title":"AdapterHub Playground: Simple and Flexible Few-Shot Learning with Adapters","created":"2021-08-18","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":"2306.01709","title":"Distilling Efficient Language-Specific Models for Cross-Lingual Transfer","created":"2023-06-02","cited_by_count":6,"area":null},{"id":"2307.03104","title":"Efficient Domain Adaptation of Sentence Embeddings Using Adapters","created":"2023-07-06","cited_by_count":6,"area":null},{"id":"2107.10523","title":"Target-Oriented Fine-tuning for Zero-Resource Named Entity Recognition","created":"2021-07-22","cited_by_count":5,"area":null},{"id":"2211.11724","title":"Legal and Political Stance Detection of SCOTUS Language","created":"2022-11-21","cited_by_count":5,"area":null},{"id":"2202.13654","title":"Cross-Lingual Text Classification with Multilingual Distillation and Zero-Shot-Aware Training","created":"2022-02-28","cited_by_count":3,"area":null},{"id":"2210.14469","title":"Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2305.11449","title":"Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast","created":"2023-05-19","cited_by_count":2,"area":null},{"id":"2205.08497","title":"Feature Aggregation in Zero-Shot Cross-Lingual Transfer Using Multilingual BERT","created":"2022-05-17","cited_by_count":1,"area":null},{"id":"2501.06025","title":"How to Tune a Multilingual Encoder Model for Germanic Languages: A Study of PEFT, Full Fine-Tuning, and Language Adapters","created":"2025-01-10","cited_by_count":0,"area":null}],"next_cursor":null}