{"total":153,"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":"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":"2105.09680","title":"KLUE: Korean Language Understanding Evaluation","created":"2021-05-20","cited_by_count":114,"area":null},{"id":"2109.07684","title":"Language Models are Few-shot Multilingual Learners","created":"2021-09-16","cited_by_count":92,"area":null},{"id":"2404.00929","title":"A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias","created":"2024-04-01","cited_by_count":84,"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":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2304.02020","title":"A Bibliometric Review of Large Language Models Research from 2017 to 2023","created":"2023-04-03","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":"2202.01159","title":"L3Cube-MahaCorpus and MahaBERT: Marathi Monolingual Corpus, Marathi BERT Language Models, and Resources","created":"2022-02-02","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":"2212.10758","title":"ORCA: A Challenging Benchmark for Arabic Language Understanding","created":"2022-12-21","cited_by_count":47,"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":"2104.14694","title":"Let's Play Mono-Poly: BERT Can Reveal Words' Polysemy Level and Partitionability into Senses","created":"2021-04-29","cited_by_count":39,"area":null},{"id":"2107.06419","title":"FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks","created":"2021-07-13","cited_by_count":39,"area":null},{"id":"2204.04541","title":"KOBEST: Korean Balanced Evaluation of Significant Tasks","created":"2022-04-09","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":"2109.13582","title":"PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided MCTS Decoding","created":"2021-09-28","cited_by_count":33,"area":null},{"id":"2102.05456","title":"Civil Rephrases Of Toxic Texts With Self-Supervised Transformers","created":"2021-02-01","cited_by_count":32,"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":"2309.10931","title":"A Family of Pretrained Transformer Language Models for Russian","created":"2023-09-19","cited_by_count":27,"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":"2206.13288","title":"Discovering Salient Neurons in Deep NLP Models","created":"2022-06-27","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":"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":"2202.02842","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","created":"2022-02-06","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":"2204.08669","title":"Mono vs Multilingual BERT for Hate Speech Detection and Text Classification: A Case Study in Marathi","created":"2022-04-19","cited_by_count":16,"area":null},{"id":"2208.07864","title":"BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification","created":"2022-08-16","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":"2208.04826","title":"Compositional Evaluation on Japanese Textual Entailment and Similarity","created":"2022-08-09","cited_by_count":14,"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":"2211.13112","title":"This is the way: designing and compiling LEPISZCZE, a comprehensive NLP benchmark for Polish","created":"2022-11-23","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":"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":"2504.08716","title":"ModernBERT or DeBERTaV3? Examining Architecture and Data Influence on Transformer Encoder Models Performance","created":"2025-04-11","cited_by_count":12,"area":null},{"id":"2202.13558","title":"CINO: A Chinese Minority Pre-trained Language Model","created":"2022-02-28","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},{"id":"2108.12465","title":"Code-switched inspired losses for generic spoken dialog representations","created":"2021-08-27","cited_by_count":10,"area":null},{"id":"2502.19582","title":"Where Are We? Evaluating LLM Performance on African Languages","created":"2025-02-26","cited_by_count":10,"area":null},{"id":"2101.11363","title":"KoreALBERT: Pretraining a Lite BERT Model for Korean Language Understanding","created":"2021-01-27","cited_by_count":9,"area":null},{"id":"2109.10234","title":"BERTweetFR : Domain Adaptation of Pre-Trained Language Models for French Tweets","created":"2021-09-21","cited_by_count":9,"area":null},{"id":"2110.08554","title":"PAGnol: An Extra-Large French Generative Model","created":"2021-10-16","cited_by_count":9,"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":"2303.13310","title":"SwissBERT: The Multilingual Language Model for Switzerland","created":"2023-03-23","cited_by_count":9,"area":null},{"id":"2401.16182","title":"LLaMandement: Large Language Models for Summarization of French Legislative Proposals","created":"2024-01-29","cited_by_count":9,"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":"2306.01497","title":"Data-Efficient French Language Modeling with CamemBERTa","created":"2023-06-02","cited_by_count":8,"area":null},{"id":"2403.15882","title":"VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding","created":"2024-03-23","cited_by_count":8,"area":null},{"id":"2108.10640","title":"Are the Multilingual Models Better? Improving Czech Sentiment with Transformers","created":"2021-08-24","cited_by_count":7,"area":null},{"id":"2109.13209","title":"FQuAD2.0: French Question Answering and knowing that you know nothing","created":"2021-09-27","cited_by_count":7,"area":null},{"id":"2306.15550","title":"CamemBERT-bio: Leveraging Continual Pre-training for Cost-Effective Models on French Biomedical Data","created":"2023-06-27","cited_by_count":7,"area":null},{"id":"2412.09415","title":"Text Generation Models for Luxembourgish with Limited Data: A Balanced Multilingual Strategy","created":"2024-12-12","cited_by_count":7,"area":null},{"id":"2105.01180","title":"Scalar Adjective Identification and Multilingual Ranking","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2109.06605","title":"MDAPT: Multilingual Domain Adaptive Pretraining in a Single Model","created":"2021-09-14","cited_by_count":6,"area":null},{"id":"2111.04260","title":"Personalized Benchmarking with the Ludwig Benchmarking Toolkit","created":"2021-11-08","cited_by_count":6,"area":null},{"id":"2204.09145","title":"ALBETO and DistilBETO: Lightweight Spanish Language Models","created":"2022-04-19","cited_by_count":6,"area":null},{"id":"2207.01893","title":"ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks","created":"2022-07-05","cited_by_count":6,"area":null},{"id":"2302.07738","title":"Alloprof: a new French question-answer education dataset and its use in an information retrieval case study","created":"2023-02-10","cited_by_count":6,"area":null},{"id":"2305.13026","title":"DUMB: A Benchmark for Smart Evaluation of Dutch Models","created":"2023-05-22","cited_by_count":6,"area":null},{"id":"2309.05951","title":"Balanced and Explainable Social Media Analysis for Public Health with Large Language Models","created":"2023-09-12","cited_by_count":6,"area":null},{"id":"2403.12809","title":"Comparing Explanation Faithfulness between Multilingual and Monolingual Fine-tuned Language Models","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2405.20468","title":"MTEB-French: Resources for French Sentence Embedding Evaluation and Analysis","created":"2024-05-30","cited_by_count":6,"area":null},{"id":"2411.12986","title":"Training Bilingual LMs with Data Constraints in the Targeted Language","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2205.10233","title":"RigoBERTa: A State-of-the-Art Language Model For Spanish","created":"2022-04-27","cited_by_count":5,"area":null},{"id":"2301.10761","title":"Fillers in Spoken Language Understanding: Computational and Psycholinguistic Perspectives","created":"2023-01-25","cited_by_count":5,"area":null},{"id":"2412.07462","title":"Bilingual BSARD: Extending Statutory Article Retrieval to Dutch","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2205.10866","title":"Blackbird's language matrices (BLMs): a new benchmark to investigate disentangled generalisation in neural networks","created":"2022-05-22","cited_by_count":4,"area":null},{"id":"2207.09076","title":"Multilingual Transformer Encoders: a Word-Level Task-Agnostic Evaluation","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2306.02349","title":"bgGLUE: A Bulgarian General Language Understanding Evaluation Benchmark","created":"2023-06-04","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":"2404.05428","title":"Language Models on a Diet: Cost-Efficient Development of Encoders for Closely-Related Languages via Additional Pretraining","created":"2024-04-08","cited_by_count":4,"area":null},{"id":"2507.16442","title":"Dutch CrowS-Pairs: Adapting a Challenge Dataset for Measuring Social Biases in Language Models for Dutch","created":"2025-07-22","cited_by_count":4,"area":null},{"id":"2604.27542","title":"HATS: An Open data set Integrating Human Perception Applied to the Evaluation of Automatic Speech Recognition Metrics","created":"2026-04-30","cited_by_count":4,"area":null},{"id":"2105.01990","title":"Evaluation Of Word Embeddings From Large-Scale French Web Content","created":"2021-05-05","cited_by_count":3,"area":null},{"id":"2105.14373","title":"Sentiment analysis in tweets: an assessment study from classical to modern text representation models","created":"2021-05-29","cited_by_count":3,"area":null},{"id":"2109.11928","title":"Is the Number of Trainable Parameters All That Actually Matters?","created":"2021-09-24","cited_by_count":3,"area":null},{"id":"2112.04329","title":"JABER and SABER: Junior and Senior Arabic BERt","created":"2021-12-08","cited_by_count":3,"area":null},{"id":"2205.07303","title":"TiBERT: Tibetan Pre-trained Language Model","created":"2022-05-15","cited_by_count":3,"area":null},{"id":"2207.08305","title":"Effectiveness of French Language Models on Abstractive Dialogue Summarization Task","created":"2022-07-17","cited_by_count":3,"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":"2209.09631","title":"De-Identification of French Unstructured Clinical Notes for Machine Learning Tasks","created":"2022-09-16","cited_by_count":3,"area":null},{"id":"2212.02108","title":"Human-in-the-Loop Hate Speech Classification in a Multilingual Context","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2212.03692","title":"Transformer-Based Named Entity Recognition for French Using Adversarial Adaptation to Similar Domain Corpora","created":"2022-12-05","cited_by_count":3,"area":null},{"id":"2303.12892","title":"Improving Transformer Performance for French Clinical Notes Classification Using Mixture of Experts on a Limited Dataset","created":"2023-03-22","cited_by_count":3,"area":"moe"},{"id":"2306.07115","title":"Exploring Attention Mechanisms for Multimodal Emotion Recognition in an Emergency Call Center Corpus","created":"2023-06-12","cited_by_count":3,"area":null},{"id":"2307.15097","title":"Cascaded Cross-Modal Transformer for Request and Complaint Detection","created":"2023-07-27","cited_by_count":3,"area":null},{"id":"2312.04843","title":"FREDSum: A Dialogue Summarization Corpus for French Political Debates","created":"2023-12-08","cited_by_count":3,"area":null},{"id":"2410.05085","title":"Explanation sensitivity to the randomness of large language models: the case of journalistic text classification","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2506.21508","title":"skLEP: A Slovak General Language Understanding Benchmark","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2109.10133","title":"Are Transformers a Modern Version of ELIZA? Observations on French Object Verb Agreement","created":"2021-09-21","cited_by_count":2,"area":null},{"id":"2110.13016","title":"Generating artificial texts as substitution or complement of training data","created":"2021-10-25","cited_by_count":2,"area":null},{"id":"2112.08991","title":"ADBCMM : Acronym Disambiguation by Building Counterfactuals and Multilingual Mixing","created":"2021-12-08","cited_by_count":2,"area":null},{"id":"2202.07791","title":"Russian SuperGLUE 1.1: Revising the Lessons not Learned by Russian NLP models","created":"2022-02-15","cited_by_count":2,"area":null},{"id":"2205.10687","title":"Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding","created":"2022-05-21","cited_by_count":2,"area":null}],"next_cursor":"100"}