{"total":280,"rows":[{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763,"area":null},{"id":"2302.11640","title":"A critical look at the evaluation of GNNs under heterophily: Are we really making progress?","created":"2023-02-22","cited_by_count":343,"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":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174,"area":null},{"id":"2201.06642","title":"Towards a Cleaner Document-Oriented Multilingual Crawled Corpus","created":"2022-01-17","cited_by_count":143,"area":null},{"id":"2104.12250","title":"XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond","created":"2021-04-25","cited_by_count":114,"area":null},{"id":"2502.17387","title":"Big-Math: A Large-Scale, High-Quality Math Dataset for Reinforcement Learning in Language Models","created":"2025-02-24","cited_by_count":109,"area":"lr"},{"id":"2112.02706","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","created":"2021-12-05","cited_by_count":91,"area":null},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80,"area":null},{"id":"2405.16640","title":"A Survey of Multimodal Large Language Model from A Data-centric Perspective","created":"2024-05-26","cited_by_count":75,"area":"mllm"},{"id":"2312.17120","title":"MathPile: A Billion-Token-Scale Pretraining Corpus for Math","created":"2023-12-28","cited_by_count":67,"area":null},{"id":"2507.22062","title":"Meta CLIP 2: A Worldwide Scaling Recipe","created":"2025-07-29","cited_by_count":64,"area":"mllm"},{"id":"2103.13309","title":"Are Multilingual Models Effective in Code-Switching?","created":"2021-03-24","cited_by_count":56,"area":null},{"id":"2407.15390","title":"ALLaM: Large Language Models for Arabic and English","created":"2024-07-22","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":"2405.15613","title":"Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach","created":"2024-05-24","cited_by_count":50,"area":null},{"id":"2205.12654","title":"Bitext Mining Using Distilled Sentence Representations for Low-Resource Languages","created":"2022-05-25","cited_by_count":48,"area":"distill"},{"id":"2112.03271","title":"Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks","created":"2021-12-06","cited_by_count":46,"area":null},{"id":"2305.03915","title":"HateMM: A Multi-Modal Dataset for Hate Video Classification","created":"2023-05-06","cited_by_count":42,"area":null},{"id":"2203.01111","title":"Large-Scale Hate Speech Detection with Cross-Domain Transfer","created":"2022-03-02","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":"2411.05735","title":"Aioli: A Unified Optimization Framework for Language Model Data Mixing","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2401.10446","title":"Large Language Models are Efficient Learners of Noise-Robust Speech Recognition","created":"2024-01-19","cited_by_count":31,"area":"lr"},{"id":"2112.02714","title":"CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks","created":"2021-12-05","cited_by_count":29,"area":null},{"id":"2103.11528","title":"A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts","created":"2021-03-22","cited_by_count":25,"area":null},{"id":"2105.05926","title":"Semantic Diversity Learning for Zero-Shot Multi-label Classification","created":"2021-05-12","cited_by_count":24,"area":null},{"id":"2104.05316","title":"Better Feature Integration for Named Entity Recognition","created":"2021-04-12","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":"2109.00227","title":"Dataset for Identification of Homophobia and Transophobia in Multilingual YouTube Comments","created":"2021-09-01","cited_by_count":20,"area":null},{"id":"2102.09604","title":"Privacy-Preserving Graph Convolutional Networks for Text Classification","created":"2021-02-10","cited_by_count":19,"area":null},{"id":"2103.14916","title":"Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection","created":"2021-03-27","cited_by_count":19,"area":null},{"id":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2109.12053","title":"Monolingual and Cross-Lingual Acceptability Judgments with the Italian CoLA corpus","created":"2021-09-24","cited_by_count":18,"area":null},{"id":"2203.14266","title":"A Survey on Aspect-Based Sentiment Classification","created":"2022-03-27","cited_by_count":18,"area":null},{"id":"2103.10069","title":"Constructive and Toxic Speech Detection for Open-domain Social Media Comments in Vietnamese","created":"2021-03-18","cited_by_count":17,"area":null},{"id":"2306.11167","title":"Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Dataset","created":"2023-06-19","cited_by_count":17,"area":null},{"id":"2105.06681","title":"DaLAJ - a dataset for linguistic acceptability judgments for Swedish: Format, baseline, sharing","created":"2021-05-14","cited_by_count":16,"area":null},{"id":"2311.01149","title":"ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model","created":"2023-11-02","cited_by_count":16,"area":null},{"id":"2408.16288","title":"OpenFGL: A Comprehensive Benchmark for Federated Graph Learning","created":"2024-08-29","cited_by_count":16,"area":null},{"id":"2410.23825","title":"GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages","created":"2024-10-31","cited_by_count":16,"area":null},{"id":"2104.04715","title":"Object Priors for Classifying and Localizing Unseen Actions","created":"2021-04-10","cited_by_count":15,"area":null},{"id":"2104.07639","title":"Robust Optimization for Multilingual Translation with Imbalanced Data","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2110.04845","title":"What Makes Sentences Semantically Related: A Textual Relatedness Dataset and Empirical Study","created":"2021-10-10","cited_by_count":15,"area":null},{"id":"2203.14655","title":"Few-Shot Learning with Siamese Networks and Label Tuning","created":"2022-03-28","cited_by_count":15,"area":null},{"id":"2204.10196","title":"Multimodal Hate Speech Detection from Bengali Memes and Texts","created":"2022-04-19","cited_by_count":15,"area":null},{"id":"2304.08823","title":"Transfer to a Low-Resource Language via Close Relatives: The Case Study on Faroese","created":"2023-04-18","cited_by_count":15,"area":null},{"id":"2206.00372","title":"BD-SHS: A Benchmark Dataset for Learning to Detect Online Bangla Hate Speech in Different Social Contexts","created":"2022-06-01","cited_by_count":14,"area":null},{"id":"2310.20384","title":"Do large language models solve verbal analogies like children do?","created":"2023-10-31","cited_by_count":13,"area":null},{"id":"2510.24963","title":"Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale","created":"2025-10-28","cited_by_count":13,"area":null},{"id":"2108.13092","title":"GeoVectors: A Linked Open Corpus of OpenStreetMap Embeddings on World Scale","created":"2021-08-30","cited_by_count":12,"area":null},{"id":"2110.08388","title":"Probing as Quantifying Inductive Bias","created":"2021-10-15","cited_by_count":12,"area":null},{"id":"2111.09618","title":"To Augment or Not to Augment? A Comparative Study on Text Augmentation Techniques for Low-Resource NLP","created":"2021-11-18","cited_by_count":12,"area":null},{"id":"2212.10405","title":"AnnoBERT: Effectively Representing Multiple Annotators' Label Choices to Improve Hate Speech Detection","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2108.00524","title":"You too Brutus! Trapping Hateful Users in Social Media: Challenges, Solutions & Insights","created":"2021-08-01","cited_by_count":11,"area":null},{"id":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2101.11978","title":"Semi-automatic Generation of Multilingual Datasets for Stance Detection in Twitter","created":"2021-01-28","cited_by_count":10,"area":null},{"id":"2104.02704","title":"Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge","created":"2021-04-06","cited_by_count":10,"area":null},{"id":"2110.07333","title":"A Survey on Legal Question Answering Systems","created":"2021-10-12","cited_by_count":10,"area":null},{"id":"2110.09599","title":"Label-Descriptive Patterns and Their Application to Characterizing Classification Errors","created":"2021-10-18","cited_by_count":10,"area":null},{"id":"2211.11187","title":"L3Cube-MahaSBERT and HindSBERT: Sentence BERT Models and Benchmarking BERT Sentence Representations for Hindi and Marathi","created":"2022-11-21","cited_by_count":10,"area":null},{"id":"2307.05083","title":"Vacaspati: A Diverse Corpus of Bangla Literature","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2412.12456","title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","created":"2024-12-17","cited_by_count":10,"area":null},{"id":"2102.06551","title":"A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages","created":"2021-02-12","cited_by_count":9,"area":null},{"id":"2103.00455","title":"NLP-CUET@DravidianLangTech-EACL2021: Offensive Language Detection from Multilingual Code-Mixed Text using Transformers","created":"2021-02-28","cited_by_count":9,"area":null},{"id":"2105.09142","title":"Laughing Heads: Can Transformers Detect What Makes a Sentence Funny?","created":"2021-05-19","cited_by_count":9,"area":null},{"id":"2106.04216","title":"A Modest Pareto Optimisation Analysis of Dependency Parsers in 2021","created":"2021-06-08","cited_by_count":9,"area":null},{"id":"2207.11808","title":"ArmanEmo: A Persian Dataset for Text-based Emotion Detection","created":"2022-07-24","cited_by_count":9,"area":null},{"id":"2502.11187","title":"TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking","created":"2025-02-16","cited_by_count":9,"area":null},{"id":"2102.13129","title":"ANEA: Distant Supervision for Low-Resource Named Entity Recognition","created":"2021-02-25","cited_by_count":8,"area":null},{"id":"2110.13479","title":"Zero-Shot Action Recognition from Diverse Object-Scene Compositions","created":"2021-10-26","cited_by_count":8,"area":null},{"id":"2205.02283","title":"pyRDF2Vec: A Python Implementation and Extension of RDF2Vec","created":"2022-05-04","cited_by_count":8,"area":null},{"id":"2506.19441","title":"TTSDS2: Resources and Benchmark for Evaluating Human-Quality Text to Speech Systems","created":"2025-06-24","cited_by_count":8,"area":null},{"id":"2103.00464","title":"NLP-CUET@LT-EDI-EACL2021: Multilingual Code-Mixed Hope Speech Detection using Cross-lingual Representation Learner","created":"2021-02-28","cited_by_count":7,"area":null},{"id":"2105.01542","title":"Conversational Machine Reading Comprehension for Vietnamese Healthcare Texts","created":"2021-05-04","cited_by_count":7,"area":null},{"id":"2108.07216","title":"Partially Supervised Named Entity Recognition via the Expected Entity Ratio Loss","created":"2021-08-16","cited_by_count":7,"area":null},{"id":"2108.08759","title":"DESYR: Definition and Syntactic Representation Based Claim Detection on the Web","created":"2021-08-19","cited_by_count":7,"area":null},{"id":"2404.09565","title":"Reliability Estimation of News Media Sources: Birds of a Feather Flock Together","created":"2024-04-15","cited_by_count":7,"area":null},{"id":"2407.07630","title":"A Review of the Challenges with Massive Web-mined Corpora Used in Large Language Models Pre-Training","created":"2024-07-10","cited_by_count":7,"area":null},{"id":"2409.18193","title":"GrEmLIn: A Repository of Green Baseline Embeddings for 87 Low-Resource Languages Injected with Multilingual Graph Knowledge","created":"2024-09-26","cited_by_count":7,"area":null},{"id":"2101.03291","title":"Combating Hostility: Covid-19 Fake News and Hostile Post Detection in Social Media","created":"2021-01-09","cited_by_count":6,"area":null},{"id":"2104.04916","title":"Cross-Lingual Word Embedding Refinement by $\\ell_{1}$ Norm Optimisation","created":"2021-04-11","cited_by_count":6,"area":null},{"id":"2104.09033","title":"Production vs Perception: The Role of Individuality in Usage-Based Grammar Induction","created":"2021-04-19","cited_by_count":6,"area":null},{"id":"2105.01180","title":"Scalar Adjective Identification and Multilingual Ranking","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2109.07242","title":"Regressive Ensemble for Machine Translation Quality Evaluation","created":"2021-09-15","cited_by_count":6,"area":null},{"id":"2109.07346","title":"Introducing an Abusive Language Classification Framework for Telegram to Investigate the German Hater Community","created":"2021-09-15","cited_by_count":6,"area":null},{"id":"2110.05663","title":"Learned Construction Grammars Converge Across Registers Given Increased Exposure","created":"2021-10-12","cited_by_count":6,"area":null},{"id":"2112.00800","title":"Iconary: A Pictionary-Based Game for Testing Multimodal Communication with Drawings and Text","created":"2021-12-01","cited_by_count":6,"area":null},{"id":"2112.07055","title":"Large Language Models are not Models of Natural Language: they are Corpus Models","created":"2021-12-13","cited_by_count":6,"area":null},{"id":"2204.05042","title":"Resources for Turkish Natural Language Processing: A critical survey","created":"2022-04-11","cited_by_count":6,"area":null},{"id":"2211.14160","title":"Exposure and Emergence in Usage-Based Grammar: Computational Experiments in 35 Languages","created":"2022-11-25","cited_by_count":6,"area":null},{"id":"2301.08731","title":"Can Peanuts Fall in Love with Distributional Semantics?","created":"2023-01-20","cited_by_count":6,"area":null},{"id":"2304.02541","title":"PWESuite: Phonetic Word Embeddings and Tasks They Facilitate","created":"2023-04-05","cited_by_count":6,"area":null},{"id":"2308.08736","title":"On the Effectiveness of Log Representation for Log-based Anomaly Detection","created":"2023-08-17","cited_by_count":6,"area":null},{"id":"2402.14404","title":"On the Tip of the Tongue: Analyzing Conceptual Representation in Large Language Models with Reverse-Dictionary Probe","created":"2024-02-22","cited_by_count":6,"area":"lr"},{"id":"2103.04386","title":"Automatic Difficulty Classification of Arabic Sentences","created":"2021-03-07","cited_by_count":5,"area":null},{"id":"2104.01443","title":"Sexism detection: The first corpus in Algerian dialect with a code-switching in Arabic/ French and English","created":"2021-04-03","cited_by_count":5,"area":null},{"id":"2104.08384","title":"\"Wikily\" Supervised Neural Translation Tailored to Cross-Lingual Tasks","created":"2021-04-16","cited_by_count":5,"area":null},{"id":"2106.02293","title":"Cross-language Sentence Selection via Data Augmentation and Rationale Training","created":"2021-06-04","cited_by_count":5,"area":null},{"id":"2108.03089","title":"Cross-lingual Capsule Network for Hate Speech Detection in Social Media","created":"2021-08-06","cited_by_count":5,"area":null}],"next_cursor":"100"}