{"total":368,"rows":[{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984,"area":null},{"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":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243,"area":null},{"id":"2305.15425","title":"Language Model Tokenizers Introduce Unfairness Between Languages","created":"2023-05-17","cited_by_count":214,"area":null},{"id":"2304.05613","title":"ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning","created":"2023-04-12","cited_by_count":206,"area":null},{"id":"2307.16039","title":"Okapi: Instruction-tuned Large Language Models in Multiple Languages with Reinforcement Learning from Human Feedback","created":"2023-07-29","cited_by_count":190,"area":"alignment"},{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143,"area":null},{"id":"2204.07580","title":"mGPT: Few-Shot Learners Go Multilingual","created":"2022-04-15","cited_by_count":142,"area":null},{"id":"2108.05542","title":"AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing","created":"2021-08-12","cited_by_count":131,"area":null},{"id":"2101.00204","title":"BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla","created":"2021-01-01","cited_by_count":125,"area":null},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"area":null},{"id":"2109.00904","title":"MultiEURLEX -- A multi-lingual and multi-label legal document classification dataset for zero-shot cross-lingual transfer","created":"2021-09-02","cited_by_count":90,"area":null},{"id":"2112.06598","title":"WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models","created":"2021-12-13","cited_by_count":89,"area":null},{"id":"2308.02976","title":"Spanish Pre-trained BERT Model and Evaluation Data","created":"2023-08-06","cited_by_count":81,"area":null},{"id":"2104.07705","title":"How to Train BERT with an Academic Budget","created":"2021-04-15","cited_by_count":80,"area":null},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"area":null},{"id":"2109.04650","title":"What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers","created":"2021-09-10","cited_by_count":76,"area":null},{"id":"2301.13126","title":"LEXTREME: A Multi-Lingual and Multi-Task Benchmark for the Legal Domain","created":"2023-01-30","cited_by_count":68,"area":null},{"id":"2101.00403","title":"Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words","created":"2021-01-02","cited_by_count":63,"area":null},{"id":"2110.00806","title":"Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark","created":"2021-10-02","cited_by_count":60,"area":null},{"id":"2205.00551","title":"Gender Bias in Masked Language Models for Multiple Languages","created":"2022-05-01","cited_by_count":60,"area":null},{"id":"2104.08200","title":"IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation","created":"2021-04-16","cited_by_count":57,"area":null},{"id":"2105.01735","title":"HerBERT: Efficiently Pretrained Transformer-based Language Model for Polish","created":"2021-05-04","cited_by_count":51,"area":null},{"id":"2107.00676","title":"A Primer on Pretrained Multilingual Language Models","created":"2021-07-01","cited_by_count":49,"area":null},{"id":"2304.10411","title":"Attention Scheme Inspired Softmax Regression","created":"2023-04-20","cited_by_count":49,"area":null},{"id":"2109.11406","title":"Named Entity Recognition and Classification on Historical Documents: A Survey","created":"2021-09-23","cited_by_count":47,"area":null},{"id":"2203.07586","title":"Long Document Summarization with Top-down and Bottom-up Inference","created":"2022-03-15","cited_by_count":42,"area":null},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41,"area":null},{"id":"2108.11792","title":"A Statutory Article Retrieval Dataset in French","created":"2021-08-26","cited_by_count":40,"area":null},{"id":"2102.10684","title":"Pre-Training BERT on Arabic Tweets: Practical Considerations","created":"2021-02-21","cited_by_count":39,"area":null},{"id":"2303.09859","title":"Trained on 100 million words and still in shape: BERT meets British National Corpus","created":"2023-03-17","cited_by_count":39,"area":null},{"id":"2304.04397","title":"Randomized and Deterministic Attention Sparsification Algorithms for Over-parameterized Feature Dimension","created":"2023-04-10","cited_by_count":37,"area":null},{"id":"2502.19249","title":"Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases","created":"2025-02-26","cited_by_count":37,"area":null},{"id":"2107.07253","title":"MarIA: Spanish Language Models","created":"2021-07-15","cited_by_count":36,"area":null},{"id":"2109.04588","title":"BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation","created":"2021-09-09","cited_by_count":35,"area":null},{"id":"2305.00660","title":"An Iterative Algorithm for Rescaled Hyperbolic Functions Regression","created":"2023-05-01","cited_by_count":35,"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":"2309.17050","title":"Interpretable Long-Form Legal Question Answering with Retrieval-Augmented Large Language Models","created":"2023-09-29","cited_by_count":35,"area":"rag"},{"id":"2105.11314","title":"RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model","created":"2021-05-24","cited_by_count":33,"area":null},{"id":"2105.00827","title":"AMMU : A Survey of Transformer-based Biomedical Pretrained Language Models","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2312.13951","title":"Typhoon: Thai Large Language Models","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2405.16411","title":"Training Tensor Attention Efficiently: From Cubic to Almost Linear Time","created":"2024-05-26","cited_by_count":30,"area":null},{"id":"2301.06627","title":"Dissociating language and thought in large language models","created":"2023-01-16","cited_by_count":29,"area":"lr"},{"id":"2408.10441","title":"Goldfish: Monolingual Language Models for 350 Languages","created":"2024-08-19","cited_by_count":29,"area":null},{"id":"2106.00742","title":"A systematic review of Hate Speech automatic detection using Natural Language Processing","created":"2021-05-22","cited_by_count":27,"area":null},{"id":"2203.08459","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model","created":"2022-03-16","cited_by_count":27,"area":null},{"id":"2304.00958","title":"DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains","created":"2023-04-03","cited_by_count":27,"area":null},{"id":"2309.10931","title":"A Family of Pretrained Transformer Language Models for Russian","created":"2023-09-19","cited_by_count":27,"area":null},{"id":"2101.09635","title":"WangchanBERTa: Pretraining transformer-based Thai Language Models","created":"2021-01-24","cited_by_count":26,"area":null},{"id":"2107.07903","title":"Are Multilingual Models the Best Choice for Moderately Under-resourced Languages? A Comprehensive Assessment for Catalan","created":"2021-07-16","cited_by_count":26,"area":null},{"id":"2204.02363","title":"Towards Best Practices for Training Multilingual Dense Retrieval Models","created":"2022-04-05","cited_by_count":26,"area":null},{"id":"2301.09626","title":"Efficient Language Model Training through Cross-Lingual and Progressive Transfer Learning","created":"2023-01-23","cited_by_count":26,"area":null},{"id":"2308.00852","title":"CASSINI: Network-Aware Job Scheduling in Machine Learning Clusters","created":"2023-08-01","cited_by_count":26,"area":null},{"id":"2104.05591","title":"DATE: Detecting Anomalies in Text via Self-Supervision of Transformers","created":"2021-04-12","cited_by_count":25,"area":null},{"id":"2304.04280","title":"FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain","created":"2023-04-09","cited_by_count":25,"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":"2305.06721","title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","created":"2023-05-11","cited_by_count":24,"area":null},{"id":"2306.05871","title":"Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?","created":"2023-06-09","cited_by_count":23,"area":null},{"id":"2103.13031","title":"Czert -- Czech BERT-like Model for Language Representation","created":"2021-03-24","cited_by_count":22,"area":null},{"id":"2104.09243","title":"BERTi\\'c -- The Transformer Language Model for Bosnian, Croatian, Montenegrin and Serbian","created":"2021-04-19","cited_by_count":21,"area":null},{"id":"2202.03371","title":"Cedille: A large autoregressive French language model","created":"2022-02-07","cited_by_count":20,"area":null},{"id":"2301.09201","title":"SPEC5G: A Dataset for 5G Cellular Network Protocol Analysis","created":"2023-01-22","cited_by_count":20,"area":null},{"id":"2407.05841","title":"An Empirical Comparison of Vocabulary Expansion and Initialization Approaches for Language Models","created":"2024-07-08","cited_by_count":20,"area":null},{"id":"2107.11610","title":"Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition","created":"2021-07-24","cited_by_count":19,"area":null},{"id":"2304.07880","title":"Sabi\\'a: Portuguese Large Language Models","created":"2023-04-16","cited_by_count":19,"area":null},{"id":"2304.10158","title":"Does Manipulating Tokenization Aid Cross-Lingual Transfer? A Study on POS Tagging for Non-Standardized Languages","created":"2023-04-20","cited_by_count":19,"area":null},{"id":"2305.14463","title":"ReadMe++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment","created":"2023-05-23","cited_by_count":19,"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":"2112.04189","title":"Transformer-Based Approach for Joint Handwriting and Named Entity Recognition in Historical documents","created":"2021-12-08","cited_by_count":17,"area":null},{"id":"2207.01683","title":"Location reference recognition from texts: A survey and comparison","created":"2022-07-04","cited_by_count":17,"area":null},{"id":"2209.12325","title":"An Empirical Study on Cross-X Transfer for Legal Judgment Prediction","created":"2022-09-25","cited_by_count":16,"area":null},{"id":"2307.08352","title":"Zero-th Order Algorithm for Softmax Attention Optimization","created":"2023-07-17","cited_by_count":16,"area":null},{"id":"2402.12969","title":"Gl\\'orIA -- A Generative and Open Large Language Model for Portuguese","created":"2024-02-20","cited_by_count":16,"area":null},{"id":"2104.13997","title":"MAGMA: An Optimization Framework for Mapping Multiple DNNs on Multiple Accelerator Cores","created":"2021-04-28","cited_by_count":15,"area":null},{"id":"2106.01478","title":"Evaluating the Efficacy of Summarization Evaluation across Languages","created":"2021-06-02","cited_by_count":14,"area":null},{"id":"2106.07540","title":"Evaluating Various Tokenizers for Arabic Text Classification","created":"2021-06-14","cited_by_count":14,"area":null},{"id":"2110.01485","title":"JuriBERT: A Masked-Language Model Adaptation for French Legal Text","created":"2021-10-04","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":"2210.14328","title":"Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models","created":"2022-10-25","cited_by_count":14,"area":null},{"id":"2305.10284","title":"Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks","created":"2023-05-17","cited_by_count":14,"area":null},{"id":"2305.12092","title":"ESCOXLM-R: Multilingual Taxonomy-driven Pre-training for the Job Market Domain","created":"2023-05-20","cited_by_count":14,"area":null},{"id":"2402.05617","title":"Deep Learning-based Computational Job Market Analysis: A Survey on Skill Extraction and Classification from Job Postings","created":"2024-02-08","cited_by_count":14,"area":null},{"id":"2106.02834","title":"MergeDistill: Merging Pre-trained Language Models using Distillation","created":"2021-06-05","cited_by_count":13,"area":null},{"id":"2107.03844","title":"A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models","created":"2021-07-08","cited_by_count":13,"area":null},{"id":"2201.05051","title":"Speech Resources in the Tamasheq Language","created":"2022-01-13","cited_by_count":13,"area":null},{"id":"2205.08808","title":"Evaluation of Transfer Learning for Polish with a Text-to-Text Model","created":"2022-05-18","cited_by_count":13,"area":null},{"id":"2308.05502","title":"Bringing order into the realm of Transformer-based language models for artificial intelligence and law","created":"2023-08-10","cited_by_count":13,"area":null},{"id":"2401.16640","title":"TeenyTinyLlama: open-source tiny language models trained in Brazilian Portuguese","created":"2024-01-30","cited_by_count":13,"area":null},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2105.11223","title":"De-identification of Privacy-related Entities in Job Postings","created":"2021-05-24","cited_by_count":12,"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":"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":"2309.13482","title":"A Unified Scheme of ResNet and Softmax","created":"2023-09-23","cited_by_count":12,"area":null},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":12,"area":null},{"id":"2402.12801","title":"Few-shot clinical entity recognition in English, French and Spanish: masked language models outperform generative model prompting","created":"2024-02-20","cited_by_count":12,"area":null},{"id":"2106.13045","title":"Where are we in semantic concept extraction for Spoken Language Understanding?","created":"2021-06-24","cited_by_count":11,"area":null},{"id":"2109.15254","title":"SlovakBERT: Slovak Masked Language Model","created":"2021-09-30","cited_by_count":11,"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":"2310.03477","title":"Tik-to-Tok: Translating Language Models One Token at a Time: An Embedding Initialization Strategy for Efficient Language Adaptation","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2402.13432","title":"DrBenchmark: A Large Language Understanding Evaluation Benchmark for French Biomedical Domain","created":"2024-02-20","cited_by_count":11,"area":null}],"next_cursor":"100"}