{"total":75,"rows":[{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463,"area":null},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284,"area":null},{"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":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2101.03289","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","created":"2021-01-09","cited_by_count":68,"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":"2204.01172","title":"PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models","created":"2022-04-03","cited_by_count":40,"area":null},{"id":"2112.08786","title":"Efficient Hierarchical Domain Adaptation for Pretrained Language Models","created":"2021-12-16","cited_by_count":32,"area":null},{"id":"2101.00420","title":"Learning to Generate Task-Specific Adapters from Task Description","created":"2021-01-02","cited_by_count":28,"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":"2401.13303","title":"MaLA-500: Massive Language Adaptation of Large Language Models","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2109.04877","title":"Efficient Test Time Adapter Ensembling for Low-resource Language Varieties","created":"2021-09-10","cited_by_count":26,"area":null},{"id":"2406.03930","title":"Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art","created":"2024-06-06","cited_by_count":26,"area":null},{"id":"2203.01976","title":"Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages","created":"2022-03-03","cited_by_count":25,"area":null},{"id":"2205.09634","title":"Phylogeny-Inspired Adaptation of Multilingual Models to New Languages","created":"2022-05-19","cited_by_count":24,"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":"2110.10472","title":"Multilingual Unsupervised Neural Machine Translation with Denoising Adapters","created":"2021-10-20","cited_by_count":22,"area":null},{"id":"2203.08304","title":"Hyperdecoders: Instance-specific decoders for multi-task NLP","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2205.12148","title":"Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer","created":"2022-05-24","cited_by_count":22,"area":null},{"id":"2402.14700","title":"Unveiling Linguistic Regions in Large Language Models","created":"2024-02-22","cited_by_count":22,"area":null},{"id":"2409.18472","title":"URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base","created":"2024-09-27","cited_by_count":21,"area":null},{"id":"2106.03958","title":"Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study","created":"2021-06-07","cited_by_count":19,"area":null},{"id":"2104.08570","title":"Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems","created":"2021-04-17","cited_by_count":17,"area":null},{"id":"2203.14276","title":"Example-based Hypernetworks for Out-of-Distribution Generalization","created":"2022-03-27","cited_by_count":16,"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":"2205.10835","title":"Multilingual Machine Translation with Hyper-Adapters","created":"2022-05-22","cited_by_count":15,"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":"2105.14980","title":"Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition","created":"2021-05-31","cited_by_count":13,"area":null},{"id":"2409.19458","title":"Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach","created":"2024-09-28","cited_by_count":13,"area":null},{"id":"2410.20817","title":"The Zeno's Paradox of `Low-Resource' Languages","created":"2024-10-28","cited_by_count":12,"area":null},{"id":"2104.04736","title":"Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing","created":"2021-04-10","cited_by_count":10,"area":null},{"id":"2310.16393","title":"ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2401.06034","title":"LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization","created":"2024-01-11","cited_by_count":10,"area":null},{"id":"2204.10714","title":"Identifying Chinese Opinion Expressions with Extremely-Noisy Crowdsourcing Annotations","created":"2022-04-22","cited_by_count":9,"area":null},{"id":"2301.08115","title":"Language Embeddings Sometimes Contain Typological Generalizations","created":"2023-01-19","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":"2108.08103","title":"AdapterHub Playground: Simple and Flexible Few-Shot Learning with Adapters","created":"2021-08-18","cited_by_count":8,"area":null},{"id":"2109.04733","title":"Genre as Weak Supervision for Cross-lingual Dependency Parsing","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2203.08552","title":"Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer","created":"2022-03-16","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":"2205.11277","title":"When does Parameter-Efficient Transfer Learning Work for Machine Translation?","created":"2022-05-23","cited_by_count":7,"area":null},{"id":"2212.01304","title":"Subword-Delimited Downsampling for Better Character-Level Translation","created":"2022-12-02","cited_by_count":7,"area":null},{"id":"2405.11125","title":"A Reproducibility Study on Quantifying Language Similarity: The Impact of Missing Values in the URIEL Knowledge Base","created":"2024-05-17","cited_by_count":7,"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":"2310.12794","title":"Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2402.00149","title":"The Impact of Language Adapters in Cross-Lingual Transfer for NLU","created":"2024-01-31","cited_by_count":6,"area":null},{"id":"2203.08555","title":"Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning","created":"2022-03-16","cited_by_count":5,"area":null},{"id":"2404.15737","title":"No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement","created":"2024-04-24","cited_by_count":5,"area":null},{"id":"2407.02317","title":"Soft Language Prompts for Language Transfer","created":"2024-07-02","cited_by_count":5,"area":null},{"id":"2301.05494","title":"Multilingual Detection of Check-Worthy Claims using World Languages and Adapter Fusion","created":"2023-01-13","cited_by_count":4,"area":null},{"id":"2406.09717","title":"UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages","created":"2024-06-14","cited_by_count":4,"area":null},{"id":"2506.12450","title":"Language Surgery in Multilingual Large Language Models","created":"2025-06-14","cited_by_count":4,"area":null},{"id":"2112.05647","title":"Analysis and Prediction of NLP Models Via Task Embeddings","created":"2021-12-10","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":"2502.10140","title":"Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages","created":"2025-02-14","cited_by_count":3,"area":null},{"id":"2107.07974","title":"POS tagging, lemmatization and dependency parsing of West Frisian","created":"2021-07-16","cited_by_count":2,"area":null},{"id":"2211.00106","title":"Data-Efficient Cross-Lingual Transfer with Language-Specific Subnetworks","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2510.27183","title":"Simple Additions, Substantial Gains: Expanding Scripts, Languages, and Lineage Coverage in URIEL+","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2406.10432","title":"AMR-RE: Abstract Meaning Representations for Retrieval-Based In-Context Learning in Relation Extraction","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2406.18880","title":"SSP: Self-Supervised Prompting for Cross-Lingual Transfer to Low-Resource Languages using Large Language Models","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2410.07809","title":"No Optimal Language Set Exists for Multilingual Instruction Tuning: Insights from a Linguistically-Informed Study","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2510.13580","title":"Sparse Subnetwork Enhancement for Underrepresented Languages in Large Language Models","created":"2025-10-15","cited_by_count":1,"area":null},{"id":"2601.16629","title":"Typologically Informed Parameter Aggregation","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2206.04806","title":"Syntactic Inductive Biases for Deep Learning Methods","created":"2022-06-08","cited_by_count":0,"area":null},{"id":"2210.09428","title":"Improving Low-Resource Cross-lingual Parsing with Expected Statistic Regularization","created":"2022-10-17","cited_by_count":0,"area":null},{"id":"2403.19183","title":"Empirical Analysis for Unsupervised Universal Dependency Parse Tree Aggregation","created":"2024-03-28","cited_by_count":0,"area":null},{"id":"2506.06785","title":"Extending dependencies to the taggedPBC: Word order in transitive clauses","created":"2025-06-07","cited_by_count":0,"area":null},{"id":"2605.04500","title":"Harnessing Linguistic Dissimilarity for Language Generalization on Unseen Low-Resource Varieties","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2606.22272","title":"MixedPEFT: Combining Multiple PEFT Methods with Mixed Objectives for Unsupervised Domain Adaptation","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2609.03775","title":"Typological Feature Prediction with Large Language Models: An In-Context Learning Approach","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}