{"total":389,"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":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412,"area":null},{"id":"2306.05087","title":"PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization","created":"2023-06-08","cited_by_count":316,"area":null},{"id":"2311.16079","title":"MEDITRON-70B: Scaling Medical Pretraining for Large Language Models","created":"2023-11-27","cited_by_count":274,"area":null},{"id":"2302.03241","title":"Continual Pre-training of Language Models","created":"2023-02-07","cited_by_count":198,"area":null},{"id":"2110.15621","title":"MentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare","created":"2021-10-29","cited_by_count":161,"area":null},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147,"area":null},{"id":"2306.15006","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","created":"2023-06-26","cited_by_count":143,"area":null},{"id":"2211.00083","title":"WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain","created":"2022-10-31","cited_by_count":117,"area":null},{"id":"2103.11943","title":"BERT: A Review of Applications in Natural Language Processing and Understanding","created":"2021-03-22","cited_by_count":109,"area":null},{"id":"2305.08377","title":"Text Classification via Large Language Models","created":"2023-05-15","cited_by_count":106,"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":"2302.13485","title":"FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning","created":"2023-02-27","cited_by_count":70,"area":null},{"id":"2405.04760","title":"Large Language Models for Cyber Security: A Systematic Literature Review","created":"2024-05-08","cited_by_count":68,"area":null},{"id":"2205.02130","title":"The Limits of Word Level Differential Privacy","created":"2022-05-02","cited_by_count":63,"area":null},{"id":"2103.15721","title":"CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic Negotiation Systems","created":"2021-03-29","cited_by_count":62,"area":null},{"id":"2107.05687","title":"Revisiting Uncertainty-based Query Strategies for Active Learning with Transformers","created":"2021-07-12","cited_by_count":60,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2204.06683","title":"Revisiting Transformer-based Models for Long Document Classification","created":"2022-04-14","cited_by_count":49,"area":null},{"id":"2207.05289","title":"PLM-ICD: Automatic ICD Coding with Pretrained Language Models","created":"2022-07-12","cited_by_count":49,"area":null},{"id":"2102.01386","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","created":"2021-02-02","cited_by_count":48,"area":null},{"id":"2202.12024","title":"NoisyTune: A Little Noise Can Help You Finetune Pretrained Language Models Better","created":"2022-02-24","cited_by_count":43,"area":null},{"id":"2102.12903","title":"Self-Tuning for Data-Efficient Deep Learning","created":"2021-02-25","cited_by_count":39,"area":null},{"id":"2107.10137","title":"Improved Text Classification via Contrastive Adversarial Training","created":"2021-07-21","cited_by_count":38,"area":null},{"id":"2106.07340","title":"MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education","created":"2021-06-02","cited_by_count":37,"area":null},{"id":"2102.00875","title":"Scaling Federated Learning for Fine-tuning of Large Language Models","created":"2021-02-01","cited_by_count":36,"area":null},{"id":"2402.15043","title":"KIEval: A Knowledge-grounded Interactive Evaluation Framework for Large Language Models","created":"2024-02-23","cited_by_count":36,"area":null},{"id":"2308.10092","title":"Open, Closed, or Small Language Models for Text Classification?","created":"2023-08-19","cited_by_count":34,"area":null},{"id":"2104.07078","title":"UDALM: Unsupervised Domain Adaptation through Language Modeling","created":"2021-04-14","cited_by_count":33,"area":null},{"id":"2210.05549","title":"Continual Training of Language Models for Few-Shot Learning","created":"2022-10-11","cited_by_count":33,"area":null},{"id":"2310.07365","title":"GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning","created":"2023-10-11","cited_by_count":33,"area":null},{"id":"2502.12150","title":"Idiosyncrasies in Large Language Models","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2306.07933","title":"Understanding Telecom Language Through Large Language Models","created":"2023-06-09","cited_by_count":32,"area":null},{"id":"2103.11408","title":"L3CubeMahaSent: A Marathi Tweet-based Sentiment Analysis Dataset","created":"2021-03-21","cited_by_count":31,"area":null},{"id":"2109.06952","title":"Residual Adapters for Parameter-Efficient ASR Adaptation to Atypical and Accented Speech","created":"2021-09-14","cited_by_count":31,"area":null},{"id":"2212.02974","title":"CySecBERT: A Domain-Adapted Language Model for the Cybersecurity Domain","created":"2022-12-06","cited_by_count":31,"area":null},{"id":"2304.09972","title":"MasakhaNEWS: News Topic Classification for African languages","created":"2023-04-19","cited_by_count":31,"area":null},{"id":"2102.09665","title":"MUDES: Multilingual Detection of Offensive Spans","created":"2021-02-18","cited_by_count":30,"area":null},{"id":"2210.10880","title":"Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning","created":"2022-10-19","cited_by_count":30,"area":null},{"id":"2105.02657","title":"Improving the Faithfulness of Attention-based Explanations with Task-specific Information for Text Classification","created":"2021-05-06","cited_by_count":29,"area":null},{"id":"2305.19249","title":"Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models","created":"2023-05-30","cited_by_count":29,"area":null},{"id":"2306.03009","title":"Using Sequences of Life-events to Predict Human Lives","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2103.00543","title":"On the Utility of Gradient Compression in Distributed Training Systems","created":"2021-02-28","cited_by_count":26,"area":null},{"id":"2111.02705","title":"Benchmarking Multimodal AutoML for Tabular Data with Text Fields","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2307.03952","title":"Is ChatGPT a Good Personality Recognizer? A Preliminary Study","created":"2023-07-08","cited_by_count":26,"area":null},{"id":"2205.10162","title":"FedAdapter: Efficient Federated Learning for Modern NLP","created":"2022-05-20","cited_by_count":25,"area":null},{"id":"2302.10447","title":"Mask-guided BERT for Few Shot Text Classification","created":"2023-02-21","cited_by_count":25,"area":null},{"id":"2111.05326","title":"The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning","created":"2021-11-09","cited_by_count":23,"area":null},{"id":"2301.08986","title":"Adapting a Language Model While Preserving its General Knowledge","created":"2023-01-21","cited_by_count":23,"area":null},{"id":"2305.01711","title":"Don't Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner","created":"2023-05-02","cited_by_count":23,"area":null},{"id":"2105.05996","title":"Multilingual Offensive Language Identification for Low-resource Languages","created":"2021-05-12","cited_by_count":22,"area":null},{"id":"2205.11342","title":"The Diminishing Returns of Masked Language Models to Science","created":"2022-05-23","cited_by_count":22,"area":null},{"id":"2403.14661","title":"Towards Modeling Learner Performance with Large Language Models","created":"2024-02-29","cited_by_count":21,"area":null},{"id":"2110.06651","title":"MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction","created":"2021-10-13","cited_by_count":20,"area":null},{"id":"2309.09500","title":"PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction","created":"2023-09-18","cited_by_count":20,"area":null},{"id":"2408.09162","title":"Zero-Shot Object-Centric Representation Learning","created":"2024-08-17","cited_by_count":19,"area":null},{"id":"2301.07295","title":"Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining","created":"2023-01-18","cited_by_count":18,"area":null},{"id":"2102.00272","title":"EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction","created":"2021-01-30","cited_by_count":17,"area":null},{"id":"2106.04631","title":"On the Lack of Robust Interpretability of Neural Text Classifiers","created":"2021-06-08","cited_by_count":17,"area":null},{"id":"2102.11903","title":"Neural ranking models for document retrieval","created":"2021-02-23","cited_by_count":16,"area":null},{"id":"2111.13657","title":"Amazon SageMaker Model Monitor: A System for Real-Time Insights into Deployed Machine Learning Models","created":"2021-11-26","cited_by_count":16,"area":null},{"id":"2111.14574","title":"On the rate of convergence of a classifier based on a Transformer encoder","created":"2021-11-29","cited_by_count":16,"area":null},{"id":"2205.10773","title":"A Domain-adaptive Pre-training Approach for Language Bias Detection in News","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2403.01567","title":"ReMatch: Retrieval Enhanced Schema Matching with LLMs","created":"2024-03-03","cited_by_count":16,"area":null},{"id":"2101.05509","title":"Transformer-based Language Model Fine-tuning Methods for COVID-19 Fake News Detection","created":"2021-01-14","cited_by_count":15,"area":null},{"id":"2105.03484","title":"Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality","created":"2021-05-07","cited_by_count":15,"area":null},{"id":"2105.12848","title":"BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition","created":"2021-05-26","cited_by_count":15,"area":null},{"id":"2402.07818","title":"Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning","created":"2024-02-12","cited_by_count":14,"area":null},{"id":"2102.08655","title":"Decoding EEG Brain Activity for Multi-Modal Natural Language Processing","created":"2021-02-17","cited_by_count":13,"area":null},{"id":"2102.11498","title":"V2W-BERT: A Framework for Effective Hierarchical Multiclass Classification of Software Vulnerabilities","created":"2021-02-23","cited_by_count":13,"area":null},{"id":"2102.11573","title":"Automated Quality Assessment of Cognitive Behavioral Therapy Sessions Through Highly Contextualized Language Representations","created":"2021-02-23","cited_by_count":13,"area":null},{"id":"2109.06501","title":"conSultantBERT: Fine-tuned Siamese Sentence-BERT for Matching Jobs and Job Seekers","created":"2021-09-14","cited_by_count":13,"area":null},{"id":"2203.10581","title":"Cluster & Tune: Boost Cold Start Performance in Text Classification","created":"2022-03-20","cited_by_count":13,"area":null},{"id":"2304.09181","title":"Large Language Models Based Automatic Synthesis of Software Specifications","created":"2023-04-18","cited_by_count":13,"area":null},{"id":"2304.10740","title":"Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams","created":"2023-04-21","cited_by_count":13,"area":null},{"id":"2104.11070","title":"Adapting Long Context NLM for ASR Rescoring in Conversational Agents","created":"2021-04-21","cited_by_count":12,"area":null},{"id":"2209.05040","title":"SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning","created":"2022-09-12","cited_by_count":12,"area":null},{"id":"2211.16878","title":"Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets","created":"2022-11-30","cited_by_count":12,"area":null},{"id":"2401.13218","title":"ULTRA: Unleash LLMs' Potential for Event Argument Extraction through Hierarchical Modeling and Pair-wise Self-Refinement","created":"2024-01-24","cited_by_count":12,"area":null},{"id":"2402.04335","title":"LegalLens: Leveraging LLMs for Legal Violation Identification in Unstructured Text","created":"2024-02-06","cited_by_count":12,"area":null},{"id":"2101.02359","title":"Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English","created":"2021-01-07","cited_by_count":11,"area":null},{"id":"2202.11345","title":"Prompt-Learning for Short Text Classification","created":"2022-02-23","cited_by_count":11,"area":null},{"id":"2204.08975","title":"Detecting Text Formality: A Study of Text Classification Approaches","created":"2022-04-19","cited_by_count":11,"area":null},{"id":"2211.03491","title":"Exploiting Transformer-based Multitask Learning for the Detection of Media Bias in News Articles","created":"2022-11-07","cited_by_count":11,"area":null},{"id":"2306.14062","title":"On the Uses of Large Language Models to Interpret Ambiguous Cyberattack Descriptions","created":"2023-06-24","cited_by_count":11,"area":null},{"id":"2405.19954","title":"GenKubeSec: LLM-Based Kubernetes Misconfiguration Detection, Localization, Reasoning, and Remediation","created":"2024-05-30","cited_by_count":11,"area":null},{"id":"2408.12168","title":"FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation","created":"2024-08-22","cited_by_count":11,"area":null},{"id":"2107.10042","title":"Comparison of Czech Transformers on Text Classification Tasks","created":"2021-07-21","cited_by_count":10,"area":null},{"id":"2108.12731","title":"$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection","created":"2021-08-29","cited_by_count":10,"area":null},{"id":"2309.05317","title":"Neural Koopman prior for data assimilation","created":"2023-09-11","cited_by_count":10,"area":null},{"id":"2310.16538","title":"FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2409.05032","title":"Exploring WavLM Back-ends for Speech Spoofing and Deepfake Detection","created":"2024-09-08","cited_by_count":10,"area":null},{"id":"2410.04501","title":"Leveraging Large Language Models for Suicide Detection on Social Media with Limited Labels","created":"2024-10-06","cited_by_count":10,"area":null},{"id":"2602.20223","title":"MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning","created":"2026-02-23","cited_by_count":10,"area":null},{"id":"2207.06897","title":"Beware the Rationalization Trap! When Language Model Explainability Diverges from our Mental Models of Language","created":"2022-07-14","cited_by_count":9,"area":null},{"id":"2209.14155","title":"Automatic Analysis of Available Source Code of Top Artificial Intelligence Conference Papers","created":"2022-09-28","cited_by_count":9,"area":null},{"id":"2203.11670","title":"Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation","created":"2022-03-22","cited_by_count":8,"area":null},{"id":"2502.20204","title":"Granite Embedding Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2508.21085","title":"Granite Embedding R2 Models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2103.12428","title":"Modeling the Severity of Complaints in Social Media","created":"2021-03-23","cited_by_count":7,"area":null}],"next_cursor":"100"}