{"total":335,"rows":[{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"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":"2202.11176","title":"A New Generation of Perspective API: Efficient Multilingual Character-level Transformers","created":"2022-02-22","cited_by_count":185,"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":"2202.03829","title":"TimeLMs: Diachronic Language Models from Twitter","created":"2022-02-08","cited_by_count":131,"area":null},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118,"area":null},{"id":"2110.08534","title":"Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora","created":"2021-10-16","cited_by_count":115,"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":"2110.05006","title":"Pre-trained Language Models in Biomedical Domain: A Systematic Survey","created":"2021-10-11","cited_by_count":87,"area":null},{"id":"2310.12321","title":"A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4","created":"2023-10-04","cited_by_count":81,"area":null},{"id":"2105.03654","title":"Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning","created":"2021-05-08","cited_by_count":76,"area":null},{"id":"2206.14774","title":"TweetNLP: Cutting-Edge Natural Language Processing for Social Media","created":"2022-06-29","cited_by_count":71,"area":null},{"id":"2202.00126","title":"Handling Bias in Toxic Speech Detection: A Survey","created":"2022-01-26","cited_by_count":61,"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":"2306.05550","title":"Bias Against 93 Stigmatized Groups in Masked Language Models and Downstream Sentiment Classification Tasks","created":"2023-06-08","cited_by_count":51,"area":null},{"id":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50,"area":null},{"id":"2303.04222","title":"SemEval-2023 Task 10: Explainable Detection of Online Sexism","created":"2023-03-07","cited_by_count":48,"area":null},{"id":"2402.08831","title":"eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data","created":"2024-02-13","cited_by_count":46,"area":null},{"id":"2209.07562","title":"TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter","created":"2022-09-15","cited_by_count":45,"area":null},{"id":"2308.16705","title":"Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis","created":"2023-08-31","cited_by_count":45,"area":null},{"id":"2204.12811","title":"SkillSpan: Hard and Soft Skill Extraction from English Job Postings","created":"2022-04-27","cited_by_count":43,"area":null},{"id":"2306.15087","title":"WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models","created":"2023-06-26","cited_by_count":42,"area":null},{"id":"2108.01682","title":"Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation","created":"2021-08-03","cited_by_count":41,"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":"2108.01250","title":"Your fairness may vary: Pretrained language model fairness in toxic text classification","created":"2021-08-03","cited_by_count":39,"area":null},{"id":"2307.10234","title":"SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning","created":"2023-07-16","cited_by_count":38,"area":null},{"id":"2209.07065","title":"CommunityLM: Probing Partisan Worldviews from Language Models","created":"2022-09-15","cited_by_count":36,"area":null},{"id":"2108.02340","title":"Robust Transfer Learning with Pretrained Language Models through Adapters","created":"2021-08-05","cited_by_count":35,"area":null},{"id":"2401.11969","title":"Claim Detection for Automated Fact-checking: A Survey on Monolingual, Multilingual and Cross-Lingual Research","created":"2024-01-22","cited_by_count":35,"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":"2109.05074","title":"FBERT: A Neural Transformer for Identifying Offensive Content","created":"2021-09-10","cited_by_count":30,"area":null},{"id":"2104.06952","title":"The Surprising Performance of Simple Baselines for Misinformation Detection","created":"2021-04-14","cited_by_count":28,"area":null},{"id":"2210.03797","title":"Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts","created":"2022-10-07","cited_by_count":28,"area":null},{"id":"2307.01680","title":"Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation","created":"2023-07-04","cited_by_count":28,"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":"2106.06297","title":"Dynamic Language Models for Continuously Evolving Content","created":"2021-06-11","cited_by_count":27,"area":null},{"id":"2109.04607","title":"IndoBERTweet: A Pretrained Language Model for Indonesian Twitter with Effective Domain-Specific Vocabulary Initialization","created":"2021-09-10","cited_by_count":25,"area":null},{"id":"2211.03154","title":"On the Domain Adaptation and Generalization of Pretrained Language Models: A Survey","created":"2022-11-06","cited_by_count":23,"area":null},{"id":"2111.09453","title":"RoBERTuito: a pre-trained language model for social media text in Spanish","created":"2021-11-18","cited_by_count":22,"area":null},{"id":"2209.09824","title":"Twitter Topic Classification","created":"2022-09-20","cited_by_count":22,"area":null},{"id":"2204.03839","title":"Infusing Knowledge from Wikipedia to Enhance Stance Detection","created":"2022-04-08","cited_by_count":20,"area":null},{"id":"2211.05182","title":"Modeling Motivational Interviewing Strategies On An Online Peer-to-Peer Counseling Platform","created":"2022-11-09","cited_by_count":20,"area":null},{"id":"2305.01723","title":"Stance Detection: A Practical Guide to Classifying Political Beliefs in Text","created":"2023-05-02","cited_by_count":20,"area":null},{"id":"2501.06932","title":"Harnessing Large Language Models for Disaster Management: A Survey","created":"2025-01-12","cited_by_count":20,"area":null},{"id":"2209.07216","title":"TempoWiC: An Evaluation Benchmark for Detecting Meaning Shift in Social Media","created":"2022-09-15","cited_by_count":19,"area":null},{"id":"2402.14298","title":"Multi-modal Stance Detection: New Datasets and Model","created":"2024-02-22","cited_by_count":18,"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":"2306.17408","title":"LMBot: Distilling Graph Knowledge into Language Model for Graph-less Deployment in Twitter Bot Detection","created":"2023-06-30","cited_by_count":17,"area":null},{"id":"2307.00067","title":"Transformers in Healthcare: A Survey","created":"2023-06-30","cited_by_count":17,"area":null},{"id":"2104.07505","title":"Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models","created":"2021-04-15","cited_by_count":15,"area":null},{"id":"2302.03147","title":"It's about Time: Rethinking Evaluation on Rumor Detection Benchmarks using Chronological Splits","created":"2023-02-06","cited_by_count":15,"area":null},{"id":"2302.07919","title":"COVID-VTS: Fact Extraction and Verification on Short Video Platforms","created":"2023-02-15","cited_by_count":15,"area":null},{"id":"2203.09813","title":"Are You Robert or RoBERTa? Deceiving Online Authorship Attribution Models Using Neural Text Generators","created":"2022-03-18","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":"2106.00210","title":"Improving Formality Style Transfer with Context-Aware Rule Injection","created":"2021-06-01","cited_by_count":13,"area":null},{"id":"2110.03142","title":"A Comparative Study of Transformer-Based Language Models on Extractive Question Answering","created":"2021-10-07","cited_by_count":13,"area":null},{"id":"2212.10233","title":"Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study","created":"2022-12-20","cited_by_count":13,"area":null},{"id":"2402.02631","title":"Learning to Understand: Identifying Interactions via the M\\\"obius Transform","created":"2024-02-04","cited_by_count":13,"area":null},{"id":"2203.05840","title":"Automatic Identification and Classification of Bragging in Social Media","created":"2022-03-11","cited_by_count":12,"area":null},{"id":"2209.13773","title":"METS-CoV: A Dataset of Medical Entity and Targeted Sentiment on COVID-19 Related Tweets","created":"2022-09-28","cited_by_count":12,"area":null},{"id":"2310.10191","title":"VIBE: Topic-Driven Temporal Adaptation for Twitter Classification","created":"2023-10-16","cited_by_count":12,"area":null},{"id":"2402.15264","title":"DEEM: Dynamic Experienced Expert Modeling for Stance Detection","created":"2024-02-23","cited_by_count":12,"area":null},{"id":"2209.13017","title":"Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social-Text Classification","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2210.10951","title":"Automatic Document Selection for Efficient Encoder Pretraining","created":"2022-10-20","cited_by_count":11,"area":null},{"id":"2301.11125","title":"A benchmark for toxic comment classification on Civil Comments dataset","created":"2023-01-26","cited_by_count":11,"area":null},{"id":"2310.11166","title":"ViSoBERT: A Pre-Trained Language Model for Vietnamese Social Media Text Processing","created":"2023-10-17","cited_by_count":11,"area":null},{"id":"2311.01876","title":"Sentiment Analysis through LLM Negotiations","created":"2023-11-03","cited_by_count":11,"area":null},{"id":"2401.00893","title":"Social-LLM: Modeling User Behavior at Scale using Language Models and Social Network Data","created":"2023-12-31","cited_by_count":11,"area":null},{"id":"2403.19031","title":"Evaluating Large Language Models for Health-Related Text Classification Tasks with Public Social Media Data","created":"2024-03-27","cited_by_count":11,"area":null},{"id":"2111.07819","title":"Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection","created":"2021-11-15","cited_by_count":10,"area":null},{"id":"2204.02626","title":"A Weakly Supervised Propagation Model for Rumor Verification and Stance Detection with Multiple Instance Learning","created":"2022-04-06","cited_by_count":10,"area":null},{"id":"2207.10639","title":"Session-based Cyberbullying Detection in Social Media: A Survey","created":"2022-07-14","cited_by_count":10,"area":null},{"id":"2210.00465","title":"Assessing the impact of contextual information in hate speech detection","created":"2022-10-02","cited_by_count":10,"area":null},{"id":"2305.00090","title":"NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysis","created":"2023-04-28","cited_by_count":10,"area":null},{"id":"2306.06707","title":"QUERT: Continual Pre-training of Language Model for Query Understanding in Travel Domain Search","created":"2023-06-11","cited_by_count":10,"area":null},{"id":"2402.06617","title":"FaBERT: Pre-training BERT on Persian Blogs","created":"2024-02-09","cited_by_count":10,"area":null},{"id":"2403.19260","title":"NaijaHate: Evaluating Hate Speech Detection on Nigerian Twitter Using Representative Data","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2409.00222","title":"Can Large Language Models Address Open-Target Stance Detection?","created":"2024-08-30","cited_by_count":10,"area":null},{"id":"2106.09462","title":"pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks","created":"2021-06-17","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":"2201.07281","title":"Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis","created":"2022-01-18","cited_by_count":9,"area":null},{"id":"2206.07360","title":"SciTweets -- A Dataset and Annotation Framework for Detecting Scientific Online Discourse","created":"2022-06-15","cited_by_count":9,"area":null},{"id":"2310.14757","title":"SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research","created":"2023-10-23","cited_by_count":9,"area":null},{"id":"2312.10467","title":"TrojFSP: Trojan Insertion in Few-shot Prompt Tuning","created":"2023-12-16","cited_by_count":9,"area":null},{"id":"2203.09178","title":"Multilingual Detection of Personal Employment Status on Twitter","created":"2022-03-17","cited_by_count":8,"area":null},{"id":"2210.03235","title":"Improving Large-scale Paraphrase Acquisition and Generation","created":"2022-10-06","cited_by_count":8,"area":null},{"id":"2210.15954","title":"Stanceosaurus: Classifying Stance Towards Multilingual Misinformation","created":"2022-10-28","cited_by_count":8,"area":null},{"id":"2309.06503","title":"Leveraging Large Language Models and Weak Supervision for Social Media data annotation: an evaluation using COVID-19 self-reported vaccination tweets","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2310.13024","title":"Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt","created":"2023-10-19","cited_by_count":8,"area":null},{"id":"2104.09742","title":"Mitigating Temporal-Drift: A Simple Approach to Keep NER Models Crisp","created":"2021-04-20","cited_by_count":7,"area":null},{"id":"2107.07970","title":"How Vulnerable Are Automatic Fake News Detection Methods to Adversarial Attacks?","created":"2021-07-16","cited_by_count":7,"area":null},{"id":"2108.02314","title":"Automatic Detection of COVID-19 Vaccine Misinformation with Graph Link Prediction","created":"2021-08-04","cited_by_count":7,"area":null},{"id":"2109.03094","title":"FHAC at GermEval 2021: Identifying German toxic, engaging, and fact-claiming comments with ensemble learning","created":"2021-09-07","cited_by_count":7,"area":null},{"id":"2110.08975","title":"Deep Transfer Learning & Beyond: Transformer Language Models in Information Systems Research","created":"2021-10-18","cited_by_count":7,"area":null},{"id":"2204.04521","title":"Benchmarking for Public Health Surveillance tasks on Social Media with a Domain-Specific Pretrained Language Model","created":"2022-04-09","cited_by_count":7,"area":null},{"id":"2210.15870","title":"\"It's Not Just Hate'': A Multi-Dimensional Perspective on Detecting Harmful Speech Online","created":"2022-10-28","cited_by_count":7,"area":null},{"id":"2211.00171","title":"Using Emotion Embeddings to Transfer Knowledge Between Emotions, Languages, and Annotation Formats","created":"2022-10-31","cited_by_count":7,"area":null},{"id":"2309.05494","title":"CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts","created":"2023-09-11","cited_by_count":7,"area":null},{"id":"2402.01980","title":"SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks","created":"2024-02-03","cited_by_count":7,"area":null},{"id":"2405.09770","title":"Optimization Techniques for Sentiment Analysis Based on LLM (GPT-3)","created":"2024-05-16","cited_by_count":7,"area":null}],"next_cursor":"100"}