{"total":255,"rows":[{"id":"2106.10199","title":"BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models","created":"2021-06-18","cited_by_count":1245,"area":null},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613,"area":null},{"id":"2110.08420","title":"Understanding Dataset Difficulty with $\\mathcal{V}$-Usable Information","created":"2021-10-16","cited_by_count":291,"area":null},{"id":"2112.08608","title":"QuALITY: Question Answering with Long Input Texts, Yes!","created":"2021-12-16","cited_by_count":208,"area":null},{"id":"2103.08493","title":"How Many Data Points is a Prompt Worth?","created":"2021-03-15","cited_by_count":198,"area":null},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192,"area":null},{"id":"2402.18013","title":"A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems","created":"2024-02-28","cited_by_count":170,"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":"2109.05687","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","created":"2021-09-13","cited_by_count":146,"area":null},{"id":"2211.15583","title":"On the Effectiveness of Parameter-Efficient Fine-Tuning","created":"2022-11-28","cited_by_count":141,"area":null},{"id":"2106.13353","title":"Cutting Down on Prompts and Parameters: Simple Few-Shot Learning with Language Models","created":"2021-06-24","cited_by_count":139,"area":null},{"id":"2305.16938","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","created":"2023-05-26","cited_by_count":136,"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":"2303.03369","title":"Multimodal Prompting with Missing Modalities for Visual Recognition","created":"2023-03-06","cited_by_count":121,"area":null},{"id":"2309.10313","title":"Investigating the Catastrophic Forgetting in Multimodal Large Language Models","created":"2023-09-19","cited_by_count":119,"area":"mllm"},{"id":"2406.07933","title":"Large Language Model Unlearning via Embedding-Corrupted Prompts","created":"2024-06-12","cited_by_count":116,"area":"safety"},{"id":"2106.07345","title":"Self-Guided Contrastive Learning for BERT Sentence Representations","created":"2021-06-03","cited_by_count":103,"area":null},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92,"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":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"area":null},{"id":"2202.07962","title":"Revisiting Parameter-Efficient Tuning: Are We Really There Yet?","created":"2022-02-16","cited_by_count":76,"area":null},{"id":"2102.04761","title":"Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data","created":"2021-02-09","cited_by_count":69,"area":null},{"id":"2211.06651","title":"NLPeer: A Unified Resource for the Computational Study of Peer Review","created":"2022-11-12","cited_by_count":60,"area":null},{"id":"2112.07869","title":"Fine-Tuning Large Neural Language Models for Biomedical Natural Language Processing","created":"2021-12-15","cited_by_count":57,"area":null},{"id":"2205.12411","title":"Linear Connectivity Reveals Generalization Strategies","created":"2022-05-24","cited_by_count":56,"area":null},{"id":"2402.12048","title":"Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models","created":"2024-02-19","cited_by_count":54,"area":"mllm"},{"id":"2405.00334","title":"A Survey on Deep Active Learning: Recent Advances and New Frontiers","created":"2024-05-01","cited_by_count":54,"area":null},{"id":"2106.05469","title":"Variational Information Bottleneck for Effective Low-Resource Fine-Tuning","created":"2021-06-10","cited_by_count":51,"area":null},{"id":"2106.01751","title":"Reordering Examples Helps during Priming-based Few-Shot Learning","created":"2021-06-03","cited_by_count":50,"area":null},{"id":"2109.03630","title":"Discrete and Soft Prompting for Multilingual Models","created":"2021-09-08","cited_by_count":49,"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":"2106.14282","title":"A Closer Look at How Fine-tuning Changes BERT","created":"2021-06-27","cited_by_count":42,"area":null},{"id":"2102.12982","title":"A Primer on Contrastive Pretraining in Language Processing: Methods, Lessons Learned and Perspectives","created":"2021-02-25","cited_by_count":41,"area":null},{"id":"2106.02902","title":"BERTnesia: Investigating the capture and forgetting of knowledge in BERT","created":"2021-06-05","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":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","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":"2503.09543","title":"PolyPythias: Stability and Outliers across Fifty Language Model Pre-Training Runs","created":"2025-03-12","cited_by_count":35,"area":null},{"id":"2109.06270","title":"STraTA: Self-Training with Task Augmentation for Better Few-shot Learning","created":"2021-09-13","cited_by_count":33,"area":"synth"},{"id":"2104.08320","title":"On the Importance of Effectively Adapting Pretrained Language Models for Active Learning","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2403.14565","title":"A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Science","created":"2024-03-21","cited_by_count":31,"area":"lr"},{"id":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30,"area":null},{"id":"2206.02291","title":"Pretrained Models for Multilingual Federated Learning","created":"2022-06-06","cited_by_count":30,"area":null},{"id":"2107.04835","title":"Noise Stability Regularization for Improving BERT Fine-tuning","created":"2021-07-10","cited_by_count":29,"area":null},{"id":"2109.06050","title":"Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training","created":"2021-09-13","cited_by_count":28,"area":null},{"id":"2306.05524","title":"On the Detectability of ChatGPT Content: Benchmarking, Methodology, and Evaluation through the Lens of Academic Writing","created":"2023-06-07","cited_by_count":27,"area":null},{"id":"2407.05374","title":"Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition","created":"2024-07-07","cited_by_count":26,"area":null},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","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":"2110.08514","title":"Analyzing Dynamic Adversarial Training Data in the Limit","created":"2021-10-16","cited_by_count":24,"area":null},{"id":"2109.04144","title":"Avoiding Inference Heuristics in Few-shot Prompt-based Finetuning","created":"2021-09-09","cited_by_count":23,"area":null},{"id":"2204.03293","title":"CoCoSoDa: Effective Contrastive Learning for Code Search","created":"2022-04-07","cited_by_count":22,"area":null},{"id":"2304.01910","title":"On the Variance of Neural Network Training with respect to Test Sets and Distributions","created":"2023-04-04","cited_by_count":22,"area":null},{"id":"2305.13073","title":"Text-to-SQL Error Correction with Language Models of Code","created":"2023-05-22","cited_by_count":21,"area":null},{"id":"2109.03685","title":"Open Aspect Target Sentiment Classification with Natural Language Prompts","created":"2021-09-08","cited_by_count":20,"area":null},{"id":"2211.08358","title":"MEAL: Stable and Active Learning for Few-Shot Prompting","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2403.04780","title":"Graph-oriented Instruction Tuning of Large Language Models for Generic Graph Mining","created":"2024-03-02","cited_by_count":20,"area":null},{"id":"2107.10314","title":"Small-Text: Active Learning for Text Classification in Python","created":"2021-07-21","cited_by_count":19,"area":null},{"id":"2206.01859","title":"Extreme Compression for Pre-trained Transformers Made Simple and Efficient","created":"2022-06-04","cited_by_count":19,"area":"distill"},{"id":"2108.11696","title":"Rethinking Why Intermediate-Task Fine-Tuning Works","created":"2021-08-26","cited_by_count":18,"area":null},{"id":"2112.08656","title":"DREAM: Improving Situational QA by First Elaborating the Situation","created":"2021-12-16","cited_by_count":18,"area":null},{"id":"2211.01642","title":"Fine-Tuning Pre-Trained Language Models Effectively by Optimizing Subnetworks Adaptively","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2302.05619","title":"Evaluating the Robustness of Discrete Prompts","created":"2023-02-11","cited_by_count":18,"area":null},{"id":"2402.12819","title":"Comparing Specialised Small and General Large Language Models on Text Classification: 100 Labelled Samples to Achieve Break-Even Performance","created":"2024-02-20","cited_by_count":18,"area":null},{"id":"2405.10808","title":"ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios","created":"2024-05-17","cited_by_count":18,"area":null},{"id":"2401.06643","title":"Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation","created":"2024-01-12","cited_by_count":17,"area":null},{"id":"2101.06779","title":"Few Shot Dialogue State Tracking using Meta-learning","created":"2021-01-17","cited_by_count":16,"area":null},{"id":"2206.02457","title":"Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives","created":"2022-06-06","cited_by_count":16,"area":null},{"id":"2209.12325","title":"An Empirical Study on Cross-X Transfer for Legal Judgment Prediction","created":"2022-09-25","cited_by_count":16,"area":null},{"id":"2401.12406","title":"Enhancing In-context Learning via Linear Probe Calibration","created":"2024-01-22","cited_by_count":16,"area":"mechinterp"},{"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":"2305.12563","title":"A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers","created":"2023-05-21","cited_by_count":15,"area":"lr"},{"id":"2201.12501","title":"Does Transliteration Help Multilingual Language Modeling?","created":"2022-01-29","cited_by_count":14,"area":null},{"id":"2210.05043","title":"Multi-CLS BERT: An Efficient Alternative to Traditional Ensembling","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2301.02998","title":"InPars-Light: Cost-Effective Unsupervised Training of Efficient Rankers","created":"2023-01-08","cited_by_count":14,"area":null},{"id":"2306.10087","title":"ActiveGLAE: A Benchmark for Deep Active Learning with Transformers","created":"2023-06-16","cited_by_count":14,"area":null},{"id":"2307.09378","title":"Adapting an ASR Foundation Model for Spoken Language Assessment","created":"2023-07-13","cited_by_count":14,"area":null},{"id":"2312.01082","title":"A Survey on Stability of Learning with Limited Labelled Data and its Sensitivity to the Effects of Randomness","created":"2023-12-02","cited_by_count":14,"area":null},{"id":"2601.06748","title":"On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning","created":"2026-01-11","cited_by_count":14,"area":"vla"},{"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":"2210.13393","title":"We need to talk about random seeds","created":"2022-10-24","cited_by_count":13,"area":null},{"id":"2211.17135","title":"BudgetLongformer: Can we Cheaply Pretrain a SotA Legal Language Model From Scratch?","created":"2022-11-30","cited_by_count":13,"area":null},{"id":"2306.10790","title":"Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference","created":"2023-06-19","cited_by_count":13,"area":null},{"id":"2311.04900","title":"How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure","created":"2023-11-08","cited_by_count":13,"area":null},{"id":"2311.07715","title":"PolyIE: A Dataset of Information Extraction from Polymer Material Scientific Literature","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2206.05658","title":"Improving Pre-trained Language Model Fine-tuning with Noise Stability Regularization","created":"2022-06-12","cited_by_count":12,"area":null},{"id":"2311.04547","title":"Large GPT-like Models are Bad Babies: A Closer Look at the Relationship between Linguistic Competence and Psycholinguistic Measures","created":"2023-11-08","cited_by_count":11,"area":null},{"id":"2105.13608","title":"Not Far Away, Not So Close: Sample Efficient Nearest Neighbour Data Augmentation via MiniMax","created":"2021-05-28","cited_by_count":10,"area":null},{"id":"2205.11603","title":"Representation Projection Invariance Mitigates Representation Collapse","created":"2022-05-23","cited_by_count":10,"area":null},{"id":"2310.17588","title":"PAC-tuning:Fine-tuning Pretrained Language Models with PAC-driven Perturbed Gradient Descent","created":"2023-10-26","cited_by_count":10,"area":null},{"id":"2404.14316","title":"Automated Long Answer Grading with RiceChem Dataset","created":"2024-04-22","cited_by_count":10,"area":null},{"id":"2503.07329","title":"Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2101.06984","title":"Studying Catastrophic Forgetting in Neural Ranking Models","created":"2021-01-18","cited_by_count":9,"area":null},{"id":"2205.13722","title":"Can Foundation Models Help Us Achieve Perfect Secrecy?","created":"2022-05-27","cited_by_count":9,"area":null},{"id":"2311.02271","title":"FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization","created":"2023-11-03","cited_by_count":9,"area":null},{"id":"2409.00124","title":"Leveraging Large Language Models for Wireless Symbol Detection via In-Context Learning","created":"2024-08-28","cited_by_count":9,"area":null},{"id":"2410.02179","title":"HATFormer: Historic Handwritten Arabic Text Recognition with Transformers","created":"2024-10-03","cited_by_count":9,"area":null},{"id":"2410.04484","title":"Fine-Grained Prediction of Reading Comprehension from Eye Movements","created":"2024-10-06","cited_by_count":9,"area":null},{"id":"2103.03335","title":"A Systematic Evaluation of Transfer Learning and Pseudo-labeling with BERT-based Ranking Models","created":"2021-03-04","cited_by_count":8,"area":null},{"id":"2204.05208","title":"\"FIJO\": a French Insurance Soft Skill Detection Dataset","created":"2022-04-11","cited_by_count":8,"area":null}],"next_cursor":"100"}