{"total":162,"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":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284,"area":null},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256,"area":null},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221,"area":null},{"id":"2111.09839","title":"Training Neural Networks with Fixed Sparse Masks","created":"2021-11-18","cited_by_count":214,"area":null},{"id":"2203.03580","title":"The Unsurprising Effectiveness of Pre-Trained Vision Models for Control","created":"2022-03-07","cited_by_count":155,"area":null},{"id":"2112.09153","title":"An Empirical Investigation of the Role of Pre-training in Lifelong Learning","created":"2021-12-16","cited_by_count":134,"area":null},{"id":"2201.08531","title":"Black-box Prompt Learning for Pre-trained Language Models","created":"2022-01-21","cited_by_count":70,"area":null},{"id":"2101.03289","title":"Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processing","created":"2021-01-09","cited_by_count":68,"area":null},{"id":"2212.08860","title":"Pre-Trained Image Encoder for Generalizable Visual Reinforcement Learning","created":"2022-12-17","cited_by_count":60,"area":null},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2405.00732","title":"LoRA Land: 310 Fine-tuned LLMs that Rival GPT-4, A Technical Report","created":"2024-04-29","cited_by_count":47,"area":null},{"id":"2206.02280","title":"Annotation Error Detection: Analyzing the Past and Present for a More Coherent Future","created":"2022-06-05","cited_by_count":45,"area":null},{"id":"2411.17646","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","created":"2024-11-26","cited_by_count":44,"area":null},{"id":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"area":null},{"id":"2307.08153","title":"Analyzing Dataset Annotation Quality Management in the Wild","created":"2023-07-16","cited_by_count":41,"area":null},{"id":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40,"area":null},{"id":"2111.06977","title":"Scalable Diverse Model Selection for Accessible Transfer Learning","created":"2021-11-12","cited_by_count":40,"area":null},{"id":"2204.01172","title":"PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models","created":"2022-04-03","cited_by_count":40,"area":null},{"id":"2308.05596","title":"You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content","created":"2023-08-10","cited_by_count":39,"area":null},{"id":"2406.01775","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","created":"2024-06-03","cited_by_count":39,"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":"2408.08345","title":"5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks","created":"2024-08-15","cited_by_count":34,"area":null},{"id":"2109.06939","title":"The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders","created":"2021-09-14","cited_by_count":32,"area":null},{"id":"2403.02467","title":"Applied Causal Inference Powered by ML and AI","created":"2024-03-04","cited_by_count":30,"area":null},{"id":"2402.01935","title":"Code Representation Learning At Scale","created":"2024-02-02","cited_by_count":26,"area":null},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25,"area":null},{"id":"2305.16597","title":"Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models","created":"2023-05-26","cited_by_count":25,"area":null},{"id":"2110.08329","title":"Control Prefixes for Parameter-Efficient Text Generation","created":"2021-10-15","cited_by_count":24,"area":null},{"id":"2305.06721","title":"Advancing Neural Encoding of Portuguese with Transformer Albertina PT-*","created":"2023-05-11","cited_by_count":24,"area":null},{"id":"2306.09729","title":"Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions","created":"2023-06-16","cited_by_count":24,"area":null},{"id":"2109.04740","title":"How Does Fine-tuning Affect the Geometry of Embedding Space: A Case Study on Isotropy","created":"2021-09-10","cited_by_count":23,"area":null},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22,"area":null},{"id":"2104.06546","title":"Large-Scale Contextualised Language Modelling for Norwegian","created":"2021-04-13","cited_by_count":21,"area":null},{"id":"2112.11670","title":"Domain Adaptation with Pre-trained Transformers for Query Focused Abstractive Text Summarization","created":"2021-12-22","cited_by_count":21,"area":null},{"id":"2410.04691","title":"Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning","created":"2024-10-07","cited_by_count":21,"area":null},{"id":"2302.05779","title":"How to prepare your task head for finetuning","created":"2023-02-11","cited_by_count":19,"area":null},{"id":"2311.15010","title":"Adapter is All You Need for Tuning Visual Tasks","created":"2023-11-25","cited_by_count":19,"area":null},{"id":"2104.09683","title":"skweak: Weak Supervision Made Easy for NLP","created":"2021-04-19","cited_by_count":17,"area":null},{"id":"2107.01641","title":"A Theoretical Analysis of Fine-tuning with Linear Teachers","created":"2021-07-04","cited_by_count":17,"area":null},{"id":"2308.04399","title":"Fine-Tuning Games: Bargaining and Adaptation for General-Purpose Models","created":"2023-08-08","cited_by_count":17,"area":null},{"id":"2210.12050","title":"Clip-Tuning: Towards Derivative-free Prompt Learning with a Mixture of Rewards","created":"2022-10-21","cited_by_count":14,"area":null},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2503.06982","title":"Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2106.09204","title":"An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models","created":"2021-06-17","cited_by_count":12,"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":"2310.03123","title":"Efficient Federated Prompt Tuning for Black-box Large Pre-trained Models","created":"2023-10-04","cited_by_count":12,"area":null},{"id":"2105.03343","title":"Adapting by Pruning: A Case Study on BERT","created":"2021-05-07","cited_by_count":11,"area":null},{"id":"2106.06555","title":"Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network","created":"2021-06-11","cited_by_count":11,"area":null},{"id":"2112.03159","title":"UniLog: Deploy One Model and Specialize it for All Log Analysis Tasks","created":"2021-12-06","cited_by_count":11,"area":null},{"id":"2403.01754","title":"Derivative-Free Optimization for Low-Rank Adaptation in Large Language Models","created":"2024-03-04","cited_by_count":11,"area":null},{"id":"2107.00439","title":"What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis","created":"2021-07-01","cited_by_count":9,"area":null},{"id":"2302.04723","title":"Zero-Shot Learning for Requirements Classification: An Exploratory Study","created":"2023-02-09","cited_by_count":9,"area":null},{"id":"2310.18877","title":"Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition","created":"2023-10-29","cited_by_count":9,"area":null},{"id":"2102.05757","title":"Customizing Contextualized Language Models forLegal Document Reviews","created":"2021-02-10","cited_by_count":8,"area":null},{"id":"2106.02382","title":"Annotation Curricula to Implicitly Train Non-Expert Annotators","created":"2021-06-04","cited_by_count":8,"area":null},{"id":"2202.08316","title":"FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2305.00593","title":"Reliable Gradient-free and Likelihood-free Prompt Tuning","created":"2023-04-30","cited_by_count":8,"area":null},{"id":"2305.16799","title":"To Revise or Not to Revise: Learning to Detect Improvable Claims for Argumentative Writing Support","created":"2023-05-26","cited_by_count":8,"area":null},{"id":"2305.17442","title":"Weaker Than You Think: A Critical Look at Weakly Supervised Learning","created":"2023-05-27","cited_by_count":8,"area":null},{"id":"2312.00909","title":"LLM-TAKE: Theme Aware Keyword Extraction Using Large Language Models","created":"2023-12-01","cited_by_count":8,"area":null},{"id":"2102.09761","title":"Scaling Creative Inspiration with Fine-Grained Functional Aspects of Ideas","created":"2021-02-19","cited_by_count":7,"area":null},{"id":"2104.07456","title":"Effect of Post-processing on Contextualized Word Representations","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2210.11255","title":"Evidence > Intuition: Transferability Estimation for Encoder Selection","created":"2022-10-20","cited_by_count":7,"area":null},{"id":"2305.16638","title":"Adversarial Multi-task Learning for End-to-end Metaphor Detection","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2305.18357","title":"DeepSI: Interactive Deep Learning for Semantic Interaction","created":"2023-05-26","cited_by_count":7,"area":null},{"id":"2101.11492","title":"On the Evolution of Syntactic Information Encoded by BERT's Contextualized Representations","created":"2021-01-27","cited_by_count":6,"area":null},{"id":"2102.02111","title":"Introduction to Neural Transfer Learning with Transformers for Social Science Text Analysis","created":"2021-02-03","cited_by_count":6,"area":null},{"id":"2208.03835","title":"On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks","created":"2022-08-07","cited_by_count":6,"area":null},{"id":"2306.09308","title":"Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2503.15779","title":"Learning Universal Human Mobility Patterns with a Foundation Model for Cross-domain Data Fusion","created":"2025-03-20","cited_by_count":6,"area":null},{"id":"2504.02122","title":"Overcoming Vocabulary Constraints with Pixel-level Fallback","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2102.03752","title":"CSS-LM: A Contrastive Framework for Semi-supervised Fine-tuning of Pre-trained Language Models","created":"2021-02-07","cited_by_count":5,"area":null},{"id":"2104.12847","title":"Morph Call: Probing Morphosyntactic Content of Multilingual Transformers","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2204.11424","title":"It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2205.00953","title":"BERTops: Studying BERT Representations under a Topological Lens","created":"2022-05-02","cited_by_count":5,"area":null},{"id":"2305.04940","title":"The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification","created":"2023-05-08","cited_by_count":5,"area":null},{"id":"2312.05356","title":"Neuron Patching: Semantic-based Neuron-level Language Model Repair for Code Generation","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2104.01940","title":"What's the best place for an AI conference, Vancouver or ______: Why completing comparative questions is difficult","created":"2021-04-05","cited_by_count":4,"area":null},{"id":"2107.05377","title":"A Flexible Multi-Task Model for BERT Serving","created":"2021-07-12","cited_by_count":4,"area":null},{"id":"2108.11809","title":"Fine-Tuning Pretrained Language Models With Label Attention for Biomedical Text Classification","created":"2021-08-26","cited_by_count":4,"area":null},{"id":"2109.07140","title":"On the Universality of Deep Contextual Language Models","created":"2021-09-15","cited_by_count":4,"area":null},{"id":"2111.06181","title":"Multilingual and Multilabel Emotion Recognition using Virtual Adversarial Training","created":"2021-11-11","cited_by_count":4,"area":null},{"id":"2203.11702","title":"BERT-ASC: Auxiliary-Sentence Construction for Implicit Aspect Learning in Sentiment Analysis","created":"2022-03-22","cited_by_count":4,"area":null},{"id":"2308.07971","title":"MultiSChuBERT: Effective Multimodal Fusion for Scholarly Document Quality Prediction","created":"2023-08-15","cited_by_count":4,"area":null},{"id":"2406.12286","title":"VIRL: Volume-Informed Representation Learning towards Few-shot Manufacturability Estimation","created":"2024-06-18","cited_by_count":4,"area":null},{"id":"2507.22337","title":"A Comprehensive Taxonomy of Negation for NLP and Neural Retrievers","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2106.15986","title":"Cross-lingual alignments of ELMo contextual embeddings","created":"2021-06-30","cited_by_count":3,"area":null},{"id":"2108.03334","title":"Towards Zero-shot Language Modeling","created":"2021-08-06","cited_by_count":3,"area":null},{"id":"2205.11113","title":"What Drives the Use of Metaphorical Language? Negative Insights from Abstractness, Affect, Discourse Coherence and Contextualized Word Representations","created":"2022-05-23","cited_by_count":3,"area":null},{"id":"2208.09529","title":"Intersection of Parallels as an Early Stopping Criterion","created":"2022-08-19","cited_by_count":3,"area":null},{"id":"2301.07868","title":"MV-Adapter: Multimodal Video Transfer Learning for Video Text Retrieval","created":"2023-01-19","cited_by_count":3,"area":null},{"id":"2302.04046","title":"Rover: An online Spark SQL tuning service via generalized transfer learning","created":"2023-02-08","cited_by_count":3,"area":null},{"id":"2307.13897","title":"AViT: Adapting Vision Transformers for Small Skin Lesion Segmentation Datasets","created":"2023-07-26","cited_by_count":3,"area":null},{"id":"2505.07637","title":"Chronocept: Instilling a Sense of Time in Machines","created":"2025-05-12","cited_by_count":3,"area":null},{"id":"2101.07632","title":"Situation and Behavior Understanding by Trope Detection on Films","created":"2021-01-19","cited_by_count":2,"area":null},{"id":"2106.02232","title":"Language Scaling for Universal Suggested Replies Model","created":"2021-06-04","cited_by_count":2,"area":null},{"id":"2106.04935","title":"Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units","created":"2021-06-09","cited_by_count":2,"area":null}],"next_cursor":"100"}