{"total":238,"rows":[{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716,"area":null},{"id":"2106.04647","title":"Compacter: Efficient Low-Rank Hypercomplex Adapter Layers","created":"2021-06-08","cited_by_count":460,"area":null},{"id":"2107.04734","title":"Layer-wise Analysis of a Self-supervised Speech Representation Model","created":"2021-07-10","cited_by_count":298,"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":"2109.04332","title":"PPT: Pre-trained Prompt Tuning for Few-shot Learning","created":"2021-09-09","cited_by_count":232,"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":"2301.12314","title":"Progressive Prompts: Continual Learning for Language Models","created":"2023-01-29","cited_by_count":197,"area":null},{"id":"2303.05118","title":"SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model","created":"2023-03-09","cited_by_count":180,"area":null},{"id":"2104.06644","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","created":"2021-04-14","cited_by_count":177,"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":"2205.06743","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","created":"2022-05-13","cited_by_count":163,"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":"2104.08835","title":"CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP","created":"2021-04-18","cited_by_count":142,"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":"2209.11055","title":"Efficient Few-Shot Learning Without Prompts","created":"2022-09-22","cited_by_count":137,"area":null},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137,"area":null},{"id":"2104.14690","title":"Entailment as Few-Shot Learner","created":"2021-04-29","cited_by_count":123,"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":"2108.13161","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","created":"2021-08-30","cited_by_count":115,"area":null},{"id":"2204.03044","title":"Fusing finetuned models for better pretraining","created":"2022-04-06","cited_by_count":110,"area":null},{"id":"2103.11955","title":"Improving and Simplifying Pattern Exploiting Training","created":"2021-03-22","cited_by_count":97,"area":null},{"id":"2106.16163","title":"The MultiBERTs: BERT Reproductions for Robustness Analysis","created":"2021-06-30","cited_by_count":92,"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":"2307.09218","title":"A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning","created":"2023-07-16","cited_by_count":69,"area":null},{"id":"2101.00438","title":"Few-Shot Question Answering by Pretraining Span Selection","created":"2021-01-02","cited_by_count":62,"area":null},{"id":"2106.00840","title":"Comparing Test Sets with Item Response Theory","created":"2021-06-01","cited_by_count":57,"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":"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":"2205.11200","title":"BBTv2: Towards a Gradient-Free Future with Large Language Models","created":"2022-05-23","cited_by_count":53,"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":"2206.06122","title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","created":"2022-06-13","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":"2112.11668","title":"How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?","created":"2021-12-22","cited_by_count":49,"area":null},{"id":"2401.04350","title":"Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness","created":"2024-01-09","cited_by_count":48,"area":"mllm"},{"id":"2112.07708","title":"Learning to Retrieve Passages without Supervision","created":"2021-12-14","cited_by_count":46,"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":"2209.01307","title":"TransPolymer: a Transformer-based language model for polymer property predictions","created":"2022-09-03","cited_by_count":43,"area":null},{"id":"2303.05251","title":"Masked Image Modeling with Local Multi-Scale Reconstruction","created":"2023-03-09","cited_by_count":43,"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":"2107.07498","title":"FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark","created":"2021-07-15","cited_by_count":41,"area":null},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"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":"2210.09421","title":"Deepfake Text Detection: Limitations and Opportunities","created":"2022-10-17","cited_by_count":37,"area":null},{"id":"2203.09125","title":"Are Vision Transformers Robust to Spurious Correlations?","created":"2022-03-17","cited_by_count":36,"area":null},{"id":"2403.16187","title":"ALoRA: Allocating Low-Rank Adaptation for Fine-tuning Large Language Models","created":"2024-03-24","cited_by_count":36,"area":null},{"id":"2212.10525","title":"SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks","created":"2022-12-20","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":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32,"area":"safety"},{"id":"2203.01104","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","created":"2022-03-02","cited_by_count":31,"area":"moe"},{"id":"2104.07179","title":"Does Putting a Linguist in the Loop Improve NLU Data Collection?","created":"2021-04-15","cited_by_count":29,"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":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28,"area":null},{"id":"2204.01098","title":"A sequence-to-sequence approach for document-level relation extraction","created":"2022-04-03","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":"2109.03564","title":"NSP-BERT: A Prompt-based Few-Shot Learner Through an Original Pre-training Task--Next Sentence Prediction","created":"2021-09-08","cited_by_count":23,"area":null},{"id":"2309.13391","title":"D-Separation for Causal Self-Explanation","created":"2023-09-23","cited_by_count":21,"area":null},{"id":"2205.05632","title":"On Distributed Adaptive Optimization with Gradient Compression","created":"2022-05-11","cited_by_count":19,"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":"2310.19182","title":"Fast Trainable Projection for Robust Fine-Tuning","created":"2023-10-29","cited_by_count":19,"area":null},{"id":"2402.16142","title":"From Text to Transformation: A Comprehensive Review of Large Language Models' Versatility","created":"2024-02-25","cited_by_count":19,"area":null},{"id":"2104.05694","title":"On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies","created":"2021-04-12","cited_by_count":18,"area":null},{"id":"2108.11696","title":"Rethinking Why Intermediate-Task Fine-Tuning Works","created":"2021-08-26","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":"2305.17682","title":"One Network, Many Masks: Towards More Parameter-Efficient Transfer Learning","created":"2023-05-28","cited_by_count":18,"area":null},{"id":"2106.02300","title":"AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER","created":"2021-06-04","cited_by_count":17,"area":null},{"id":"2109.12742","title":"FewNLU: Benchmarking State-of-the-Art Methods for Few-Shot Natural Language Understanding","created":"2021-09-27","cited_by_count":17,"area":null},{"id":"2205.11166","title":"Prompt Tuning for Discriminative Pre-trained Language Models","created":"2022-05-23","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":"2209.06995","title":"Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach","created":"2022-09-15","cited_by_count":16,"area":null},{"id":"2507.00994","title":"Should We Still Pretrain Encoders with Masked Language Modeling?","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2203.01543","title":"QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition","created":"2022-03-03","cited_by_count":15,"area":null},{"id":"2212.05974","title":"Federated Few-Shot Learning for Mobile NLP","created":"2022-12-12","cited_by_count":15,"area":null},{"id":"2410.09112","title":"HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction","created":"2024-10-10","cited_by_count":15,"area":null},{"id":"2109.05941","title":"Efficient Contrastive Learning via Novel Data Augmentation and Curriculum Learning","created":"2021-09-10","cited_by_count":14,"area":null},{"id":"2203.10079","title":"Simulating Bandit Learning from User Feedback for Extractive Question Answering","created":"2022-03-18","cited_by_count":14,"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":"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":"2208.13474","title":"Prompt Tuning with Soft Context Sharing for Vision-Language Models","created":"2022-08-29","cited_by_count":13,"area":"mllm"},{"id":"2210.07352","title":"Predicting Fine-Tuning Performance with Probing","created":"2022-10-13","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":"2603.04964","title":"Replaying pre-training data improves fine-tuning","created":"2026-03-05","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":"2203.03878","title":"HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks","created":"2022-03-08","cited_by_count":12,"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":"2105.03343","title":"Adapting by Pruning: A Case Study on BERT","created":"2021-05-07","cited_by_count":11,"area":null},{"id":"2206.14366","title":"Knowledge Distillation of Transformer-based Language Models Revisited","created":"2022-06-29","cited_by_count":11,"area":"distill"},{"id":"2212.08853","title":"HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation","created":"2022-12-17","cited_by_count":11,"area":null},{"id":"2311.11973","title":"Adaptive Training Distributions with Scalable Online Bilevel Optimization","created":"2023-11-20","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":"2410.12178","title":"Model Balancing Helps Low-data Training and Fine-tuning","created":"2024-10-16","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":"2205.00820","title":"Entity-aware Transformers for Entity Search","created":"2022-05-02","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":"2211.01587","title":"Eliciting Knowledge from Large Pre-Trained Models for Unsupervised Knowledge-Grounded Conversation","created":"2022-11-03","cited_by_count":10,"area":null},{"id":"2212.10422","title":"Localising In-Domain Adaptation of Transformer-Based Biomedical Language Models","created":"2022-12-20","cited_by_count":10,"area":null}],"next_cursor":"100"}