{"total":125,"rows":[{"id":"2308.16884","title":"The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants","created":"2023-08-31","cited_by_count":311,"area":null},{"id":"2305.13707","title":"Do All Languages Cost the Same? Tokenization in the Era of Commercial Language Models","created":"2023-05-23","cited_by_count":192,"area":null},{"id":"2305.14456","title":"Having Beer after Prayer? Measuring Cultural Bias in Large Language Models","created":"2023-05-23","cited_by_count":153,"area":null},{"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":"2205.06266","title":"Lifting the Curse of Multilinguality by Pre-training Modular Transformers","created":"2022-05-12","cited_by_count":146,"area":null},{"id":"2110.06733","title":"Systematic Inequalities in Language Technology Performance across the World's Languages","created":"2021-10-13","cited_by_count":120,"area":null},{"id":"2109.00486","title":"Survey of Low-Resource Machine Translation","created":"2021-09-01","cited_by_count":92,"area":null},{"id":"2212.09535","title":"BLOOM+1: Adding Language Support to BLOOM for Zero-Shot Prompting","created":"2022-12-19","cited_by_count":90,"area":null},{"id":"2411.19799","title":"INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge","created":"2024-11-29","cited_by_count":86,"area":null},{"id":"2201.08277","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis","created":"2022-01-20","cited_by_count":64,"area":null},{"id":"2207.06991","title":"Language Modelling with Pixels","created":"2022-07-14","cited_by_count":55,"area":null},{"id":"2210.08523","title":"Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP World","created":"2022-10-16","cited_by_count":55,"area":null},{"id":"2106.02124","title":"How to Adapt Your Pretrained Multilingual Model to 1600 Languages","created":"2021-06-03","cited_by_count":54,"area":null},{"id":"2104.08726","title":"AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages","created":"2021-04-18","cited_by_count":50,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2203.09435","title":"Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation","created":"2022-03-17","cited_by_count":44,"area":null},{"id":"2105.07316","title":"From Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding","created":"2021-05-15","cited_by_count":43,"area":null},{"id":"2306.07377","title":"Lost in Translation: Large Language Models in Non-English Content Analysis","created":"2023-06-12","cited_by_count":35,"area":null},{"id":"2407.08818","title":"MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization","created":"2024-07-11","cited_by_count":31,"area":null},{"id":"2401.14280","title":"RomanSetu: Efficiently unlocking multilingual capabilities of Large Language Models via Romanization","created":"2024-01-25","cited_by_count":29,"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":"2203.10753","title":"Match the Script, Adapt if Multilingual: Analyzing the Effect of Multilingual Pretraining on Cross-lingual Transferability","created":"2022-03-21","cited_by_count":26,"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":"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":"2112.03497","title":"Dataset Geography: Mapping Language Data to Language Users","created":"2021-12-07","cited_by_count":22,"area":null},{"id":"2406.11477","title":"How Can We Effectively Expand the Vocabulary of LLMs with 0.01GB of Target Language Text?","created":"2024-06-17","cited_by_count":22,"area":null},{"id":"2106.09063","title":"Specializing Multilingual Language Models: An Empirical Study","created":"2021-06-16","cited_by_count":21,"area":null},{"id":"2304.08865","title":"Romanization-based Large-scale Adaptation of Multilingual Language Models","created":"2023-04-18","cited_by_count":21,"area":null},{"id":"2305.13627","title":"InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning","created":"2023-05-23","cited_by_count":21,"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":"2109.06772","title":"Improving Zero-shot Cross-lingual Transfer between Closely Related Languages by injecting Character-level Noise","created":"2021-09-14","cited_by_count":19,"area":null},{"id":"2205.03018","title":"Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users","created":"2022-05-06","cited_by_count":19,"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":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15,"area":null},{"id":"2407.01406","title":"Adapting Multilingual LLMs to Low-Resource Languages with Knowledge Graphs via Adapters","created":"2024-07-01","cited_by_count":15,"area":null},{"id":"2110.07804","title":"Alternative Input Signals Ease Transfer in Multilingual Machine Translation","created":"2021-10-15","cited_by_count":14,"area":null},{"id":"2201.12501","title":"Does Transliteration Help Multilingual Language Modeling?","created":"2022-01-29","cited_by_count":14,"area":null},{"id":"2205.10517","title":"Pre-training Data Quality and Quantity for a Low-Resource Language: New Corpus and BERT Models for Maltese","created":"2022-05-21","cited_by_count":14,"area":null},{"id":"2406.19759","title":"Breaking the Script Barrier in Multilingual Pre-Trained Language Models with Transliteration-Based Post-Training Alignment","created":"2024-06-28","cited_by_count":14,"area":null},{"id":"2406.10602","title":"Multilingual Large Language Models and Curse of Multilinguality","created":"2024-06-15","cited_by_count":13,"area":null},{"id":"2109.04556","title":"Subword Mapping and Anchoring across Languages","created":"2021-09-09","cited_by_count":12,"area":null},{"id":"2212.12510","title":"MicroBERT: Effective Training of Low-resource Monolingual BERTs through Parameter Reduction and Multitask Learning","created":"2022-12-23","cited_by_count":12,"area":null},{"id":"2312.07141","title":"Multilingual large language models leak human stereotypes across language boundaries","created":"2023-12-12","cited_by_count":12,"area":null},{"id":"2506.10766","title":"One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers","created":"2025-06-12","cited_by_count":12,"area":null},{"id":"2110.13658","title":"Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?","created":"2021-10-26","cited_by_count":11,"area":null},{"id":"2307.04361","title":"Enhancing Cross-lingual Transfer via Phonemic Transcription Integration","created":"2023-07-10","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":"2303.04715","title":"Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results","created":"2023-03-08","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":"2202.12312","title":"Oolong: Investigating What Makes Transfer Learning Hard with Controlled Studies","created":"2022-02-24","cited_by_count":9,"area":null},{"id":"2205.11152","title":"Cross-lingual Lifelong Learning","created":"2022-05-23","cited_by_count":9,"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":"2405.12413","title":"Targeted Multilingual Adaptation for Low-resource Language Families","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2105.14115","title":"Towards More Equitable Question Answering Systems: How Much More Data Do You Need?","created":"2021-05-28","cited_by_count":8,"area":null},{"id":"2205.09744","title":"Overcoming Language Disparity in Online Content Classification with Multimodal Learning","created":"2022-05-19","cited_by_count":8,"area":null},{"id":"2412.10244","title":"Efficient Continual Pre-training of LLMs for Low-resource Languages","created":"2024-12-13","cited_by_count":8,"area":null},{"id":"2206.04371","title":"Ancestor-to-Creole Transfer is Not a Walk in the Park","created":"2022-06-09","cited_by_count":7,"area":null},{"id":"2209.09368","title":"The first neural machine translation system for the Erzya language","created":"2022-09-19","cited_by_count":7,"area":null},{"id":"2403.20088","title":"An Efficient Approach for Studying Cross-Lingual Transfer in Multilingual Language Models","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2204.04873","title":"Adapting BigScience Multilingual Model to Unseen Languages","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2210.12273","title":"Graphemic Normalization of the Perso-Arabic Script","created":"2022-10-21","cited_by_count":6,"area":null},{"id":"2402.14279","title":"Mitigating the Linguistic Gap with Phonemic Representations for Robust Cross-lingual Transfer","created":"2024-02-22","cited_by_count":6,"area":null},{"id":"2408.04628","title":"LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP","created":"2024-08-08","cited_by_count":6,"area":null},{"id":"2409.17326","title":"How Transliterations Improve Crosslingual Alignment","created":"2024-09-25","cited_by_count":6,"area":null},{"id":"2411.02398","title":"Prompting with Phonemes: Enhancing LLMs' Multilinguality for Non-Latin Script Languages","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2204.06457","title":"The Impact of Cross-Lingual Adjustment of Contextual Word Representations on Zero-Shot Transfer","created":"2022-04-13","cited_by_count":5,"area":null},{"id":"2401.16895","title":"Cross-Lingual Transfer from Related Languages: Treating Low-Resource Maltese as Multilingual Code-Switching","created":"2024-01-30","cited_by_count":5,"area":null},{"id":"2412.14050","title":"Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation","created":"2024-12-18","cited_by_count":5,"area":null},{"id":"2302.07912","title":"Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models","created":"2023-02-15","cited_by_count":4,"area":null},{"id":"2310.08078","title":"To token or not to token: A Comparative Study of Text Representations for Cross-Lingual Transfer","created":"2023-10-12","cited_by_count":4,"area":null},{"id":"2311.08348","title":"MC$^2$: Towards Transparent and Culturally-Aware NLP for Minority Languages in China","created":"2023-11-14","cited_by_count":4,"area":null},{"id":"2403.08693","title":"Do Language Models Care About Text Quality? Evaluating Web-Crawled Corpora Across 11 Languages","created":"2024-03-13","cited_by_count":4,"area":null},{"id":"2404.12618","title":"CORI: CJKV Benchmark with Romanization Integration -- A step towards Cross-lingual Transfer Beyond Textual Scripts","created":"2024-04-19","cited_by_count":4,"area":null},{"id":"2404.18286","title":"Comparing LLM prompting with Cross-lingual transfer performance on Indigenous and Low-resource Brazilian Languages","created":"2024-04-28","cited_by_count":4,"area":null},{"id":"2103.13272","title":"Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages","created":"2021-03-24","cited_by_count":3,"area":null},{"id":"2210.06068","title":"Investigating Massive Multilingual Pre-Trained Machine Translation Models for Clinical Domain via Transfer Learning","created":"2022-10-12","cited_by_count":3,"area":null},{"id":"2211.15965","title":"Extending the Subwording Model of Multilingual Pretrained Models for New Languages","created":"2022-11-29","cited_by_count":3,"area":null},{"id":"2306.08702","title":"Does mBERT understand Romansh? Evaluating word embeddings using word alignment","created":"2023-06-14","cited_by_count":3,"area":null},{"id":"2401.05811","title":"Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages","created":"2024-01-11","cited_by_count":3,"area":null},{"id":"2401.06620","title":"TransliCo: A Contrastive Learning Framework to Address the Script Barrier in Multilingual Pretrained Language Models","created":"2024-01-12","cited_by_count":3,"area":null},{"id":"2412.13375","title":"Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation","created":"2024-12-17","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":"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":"2508.11017","title":"Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics","created":"2025-08-14","cited_by_count":3,"area":null},{"id":"2512.10772","title":"Grow Up and Merge: Scaling Strategies for Efficient Language Adaptation","created":"2025-12-11","cited_by_count":3,"area":null},{"id":"2604.05090","title":"Multilingual Language Models Encode Script Over Linguistic Structure","created":"2026-04-06","cited_by_count":3,"area":null},{"id":"2304.09957","title":"Low-resource Bilingual Dialect Lexicon Induction with Large Language Models","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2304.12979","title":"GMNLP at SemEval-2023 Task 12: Sentiment Analysis with Phylogeny-Based Adapters","created":"2023-04-25","cited_by_count":2,"area":null},{"id":"2401.14400","title":"Modular Adaptation of Multilingual Encoders to Written Swiss German Dialect","created":"2024-01-25","cited_by_count":2,"area":null},{"id":"2404.18810","title":"Unknown Script: Impact of Script on Cross-Lingual Transfer","created":"2024-04-29","cited_by_count":2,"area":null},{"id":"2409.18199","title":"LangSAMP: Language-Script Aware Multilingual Pretraining","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2506.04385","title":"MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP","created":"2025-06-04","cited_by_count":2,"area":null},{"id":"2508.17078","title":"Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languages","created":"2025-08-23","cited_by_count":2,"area":null},{"id":"2509.25516","title":"Beyond WER: Probing Whisper's Sub-token Decoder Across Diverse Language Resource Levels","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.10827","title":"Happiness is Sharing a Vocabulary: A Study of Transliteration Methods","created":"2025-10-12","cited_by_count":2,"area":null},{"id":"2602.05648","title":"Modelling the Morphology of Verbal Paradigms: A Case Study in the Tokenization of Turkish and Hebrew","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2301.09685","title":"Noisy Parallel Data Alignment","created":"2023-01-23","cited_by_count":1,"area":null}],"next_cursor":"100"}