{"total":1082,"rows":[{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234,"area":null},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744,"area":null},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394,"area":null},{"id":"2104.05938","title":"QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization","created":"2021-04-13","cited_by_count":365,"area":null},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2204.06031","title":"A Review on Language Models as Knowledge Bases","created":"2022-04-12","cited_by_count":157,"area":null},{"id":"2210.14709","title":"Learning on Large-scale Text-attributed Graphs via Variational Inference","created":"2022-10-26","cited_by_count":155,"area":null},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125,"area":null},{"id":"2101.09459","title":"Advances and Challenges in Conversational Recommender Systems: A Survey","created":"2021-01-23","cited_by_count":118,"area":null},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115,"area":null},{"id":"2104.07186","title":"COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List","created":"2021-04-15","cited_by_count":113,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"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":"2203.05797","title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","created":"2022-03-11","cited_by_count":108,"area":null},{"id":"2305.08377","title":"Text Classification via Large Language Models","created":"2023-05-15","cited_by_count":106,"area":null},{"id":"2112.02706","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","created":"2021-12-05","cited_by_count":91,"area":null},{"id":"2112.10070","title":"Unified Named Entity Recognition as Word-Word Relation Classification","created":"2021-12-19","cited_by_count":90,"area":null},{"id":"2302.13939","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","created":"2023-02-27","cited_by_count":88,"area":null},{"id":"2103.15049","title":"HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval","created":"2021-03-28","cited_by_count":87,"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":"2105.13562","title":"ILDC for CJPE: Indian Legal Documents Corpus for Court Judgment Prediction and Explanation","created":"2021-05-28","cited_by_count":78,"area":null},{"id":"2103.08902","title":"Differentiable Learning Under Triage","created":"2021-03-16","cited_by_count":76,"area":null},{"id":"2212.14548","title":"How would Stance Detection Techniques Evolve after the Launch of ChatGPT?","created":"2022-12-30","cited_by_count":76,"area":null},{"id":"2206.08451","title":"I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences","created":"2022-06-16","cited_by_count":75,"area":null},{"id":"2105.05727","title":"BertGCN: Transductive Text Classification by Combining GCN and BERT","created":"2021-05-12","cited_by_count":74,"area":null},{"id":"2106.01978","title":"DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations","created":"2021-06-03","cited_by_count":71,"area":null},{"id":"2203.04592","title":"Mapping global dynamics of benchmark creation and saturation in artificial intelligence","created":"2022-03-09","cited_by_count":71,"area":null},{"id":"2202.03673","title":"Calibrated Learning to Defer with One-vs-All Classifiers","created":"2022-02-08","cited_by_count":69,"area":null},{"id":"2201.00987","title":"MDFEND: Multi-domain Fake News Detection","created":"2022-01-04","cited_by_count":68,"area":null},{"id":"2108.13230","title":"AEDA: An Easier Data Augmentation Technique for Text Classification","created":"2021-08-30","cited_by_count":67,"area":null},{"id":"2203.16797","title":"When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning","created":"2022-03-31","cited_by_count":65,"area":null},{"id":"2209.06015","title":"Black-box Dataset Ownership Verification via Backdoor Watermarking","created":"2022-08-04","cited_by_count":65,"area":null},{"id":"2102.06732","title":"Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution","created":"2021-01-24","cited_by_count":64,"area":null},{"id":"2106.12735","title":"Multi-Modal 3D Object Detection in Autonomous Driving: a Survey","created":"2021-06-24","cited_by_count":63,"area":null},{"id":"2108.04556","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","created":"2021-08-10","cited_by_count":63,"area":null},{"id":"2203.01054","title":"A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges","created":"2022-03-02","cited_by_count":61,"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":"2210.16955","title":"Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles","created":"2022-10-30","cited_by_count":60,"area":null},{"id":"2104.13030","title":"A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation","created":"2021-04-27","cited_by_count":59,"area":null},{"id":"2202.04301","title":"Log-based Anomaly Detection with Deep Learning: How Far Are We?","created":"2022-02-09","cited_by_count":57,"area":null},{"id":"2311.10944","title":"Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networks","created":"2023-11-18","cited_by_count":56,"area":null},{"id":"2106.00641","title":"SpanNER: Named Entity Re-/Recognition as Span Prediction","created":"2021-06-01","cited_by_count":55,"area":null},{"id":"2104.15135","title":"Explanation-Based Human Debugging of NLP Models: A Survey","created":"2021-04-30","cited_by_count":53,"area":null},{"id":"2304.03347","title":"Towards Interpretable Mental Health Analysis with Large Language Models","created":"2023-04-06","cited_by_count":53,"area":null},{"id":"2203.02385","title":"MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations","created":"2022-03-04","cited_by_count":52,"area":null},{"id":"2406.11289","title":"A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models","created":"2024-06-17","cited_by_count":52,"area":null},{"id":"2205.12424","title":"VulBERTa: Simplified Source Code Pre-Training for Vulnerability Detection","created":"2022-05-25","cited_by_count":51,"area":null},{"id":"2310.15515","title":"Fighting Fire with Fire: The Dual Role of LLMs in Crafting and Detecting Elusive Disinformation","created":"2023-10-24","cited_by_count":51,"area":null},{"id":"2102.06314","title":"Embracing Domain Differences in Fake News: Cross-domain Fake News Detection using Multi-modal Data","created":"2021-02-11","cited_by_count":50,"area":null},{"id":"2103.12057","title":"An Experimental Review on Deep Learning Architectures for Time Series Forecasting","created":"2021-03-22","cited_by_count":47,"area":null},{"id":"2312.06337","title":"Deep Imbalanced Learning for Multimodal Emotion Recognition in Conversations","created":"2023-12-11","cited_by_count":47,"area":null},{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46,"area":null},{"id":"2110.06366","title":"Time Masking for Temporal Language Models","created":"2021-10-12","cited_by_count":46,"area":null},{"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":"2104.12840","title":"AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2203.06667","title":"Towards Visual-Prompt Temporal Answering Grounding in Medical Instructional Video","created":"2022-03-13","cited_by_count":43,"area":null},{"id":"2102.05218","title":"FLOP: Federated Learning on Medical Datasets using Partial Networks","created":"2021-02-10","cited_by_count":42,"area":null},{"id":"2108.03070","title":"SWSR: A Chinese Dataset and Lexicon for Online Sexism Detection","created":"2021-08-06","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":"2103.08490","title":"Multi-view Subword Regularization","created":"2021-03-15","cited_by_count":40,"area":null},{"id":"2103.06511","title":"Does the Magic of BERT Apply to Medical Code Assignment? A Quantitative Study","created":"2021-03-11","cited_by_count":39,"area":null},{"id":"2109.12575","title":"Paradigm Shift in Natural Language Processing","created":"2021-09-26","cited_by_count":39,"area":null},{"id":"2302.03883","title":"Multimodal Recommender Systems: A Survey","created":"2023-02-08","cited_by_count":37,"area":null},{"id":"2111.06206","title":"Defining and Quantifying the Emergence of Sparse Concepts in DNNs","created":"2021-11-11","cited_by_count":36,"area":null},{"id":"2107.02975","title":"Neural Natural Language Processing for Unstructured Data in Electronic Health Records: a Review","created":"2021-07-07","cited_by_count":35,"area":null},{"id":"2108.11626","title":"CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation","created":"2021-08-26","cited_by_count":35,"area":null},{"id":"2312.01044","title":"Large Language Models Are Zero-Shot Text Classifiers","created":"2023-12-02","cited_by_count":35,"area":null},{"id":"2101.00939","title":"CRSLab: An Open-Source Toolkit for Building Conversational Recommender System","created":"2021-01-04","cited_by_count":34,"area":null},{"id":"2102.07325","title":"Cross-modal Adversarial Reprogramming","created":"2021-02-15","cited_by_count":34,"area":null},{"id":"2103.08545","title":"A Study of Automatic Metrics for the Evaluation of Natural Language Explanations","created":"2021-03-15","cited_by_count":34,"area":null},{"id":"2105.13448","title":"Open-world Machine Learning: Applications, Challenges, and Opportunities","created":"2021-05-27","cited_by_count":34,"area":null},{"id":"2203.10885","title":"Zoom Out and Observe: News Environment Perception for Fake News Detection","created":"2022-03-21","cited_by_count":34,"area":null},{"id":"2307.16630","title":"Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks","created":"2023-07-31","cited_by_count":34,"area":null},{"id":"2102.02811","title":"CrossNorm and SelfNorm for Generalization under Distribution Shifts","created":"2021-02-04","cited_by_count":33,"area":null},{"id":"2101.10642","title":"Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks","created":"2021-01-26","cited_by_count":32,"area":null},{"id":"2110.07317","title":"ReGVD: Revisiting Graph Neural Networks for Vulnerability Detection","created":"2021-10-14","cited_by_count":32,"area":null},{"id":"2203.01677","title":"Detection of Word Adversarial Examples in Text Classification: Benchmark and Baseline via Robust Density Estimation","created":"2022-03-03","cited_by_count":32,"area":null},{"id":"2204.06923","title":"A Unified Multi-task Learning Framework for Multi-goal Conversational Recommender Systems","created":"2022-04-14","cited_by_count":32,"area":null},{"id":"2204.11786","title":"Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications","created":"2022-04-25","cited_by_count":32,"area":null},{"id":"2312.05735","title":"A Comprehensive Survey on Multi-modal Conversational Emotion Recognition with Deep Learning","created":"2023-12-10","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":"2206.12808","title":"Memory-Guided Multi-View Multi-Domain Fake News Detection","created":"2022-06-26","cited_by_count":31,"area":null},{"id":"2307.07135","title":"MMSD2.0: Towards a Reliable Multi-modal Sarcasm Detection System","created":"2023-07-14","cited_by_count":31,"area":null},{"id":"2109.05743","title":"Explain Me the Painting: Multi-Topic Knowledgeable Art Description Generation","created":"2021-09-13","cited_by_count":30,"area":null},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29,"area":null},{"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":"2204.09263","title":"User-Centric Conversational Recommendation with Multi-Aspect User Modeling","created":"2022-04-20","cited_by_count":29,"area":null},{"id":"2306.17799","title":"A Low-rank Matching Attention based Cross-modal Feature Fusion Method for Conversational Emotion Recognition","created":"2023-06-16","cited_by_count":29,"area":null},{"id":"2103.11576","title":"Grey-box Adversarial Attack And Defence For Sentiment Classification","created":"2021-03-22","cited_by_count":28,"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":"2104.10343","title":"Sensitivity as a Complexity Measure for Sequence Classification Tasks","created":"2021-04-21","cited_by_count":28,"area":null},{"id":"2105.06947","title":"Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer","created":"2021-05-14","cited_by_count":28,"area":null},{"id":"2112.02268","title":"Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding","created":"2021-12-04","cited_by_count":28,"area":null},{"id":"2205.15060","title":"Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems","created":"2022-05-30","cited_by_count":28,"area":null},{"id":"2105.03322","title":"Are Pre-trained Convolutions Better than Pre-trained Transformers?","created":"2021-05-07","cited_by_count":27,"area":null},{"id":"2202.08159","title":"Domain Adaptive Fake News Detection via Reinforcement Learning","created":"2022-02-16","cited_by_count":27,"area":null},{"id":"2210.03501","title":"Towards Multi-Modal Sarcasm Detection via Hierarchical Congruity Modeling with Knowledge Enhancement","created":"2022-10-07","cited_by_count":27,"area":null}],"next_cursor":"100"}