{"total":57,"rows":[{"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":"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":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164,"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":"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":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67,"area":null},{"id":"2307.04722","title":"Advances and Challenges in Meta-Learning: A Technical Review","created":"2023-07-10","cited_by_count":65,"area":null},{"id":"2312.03724","title":"DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer","created":"2023-11-27","cited_by_count":57,"area":null},{"id":"2303.15935","title":"When Brain-inspired AI Meets AGI","created":"2023-03-28","cited_by_count":54,"area":null},{"id":"2212.01378","title":"ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning","created":"2022-12-02","cited_by_count":52,"area":null},{"id":"2104.08808","title":"Learn Continually, Generalize Rapidly: Lifelong Knowledge Accumulation for Few-shot Learning","created":"2021-04-18","cited_by_count":35,"area":null},{"id":"2110.08458","title":"Controllable Semantic Parsing via Retrieval Augmentation","created":"2021-10-16","cited_by_count":35,"area":null},{"id":"2306.12509","title":"Joint Prompt Optimization of Stacked LLMs using Variational Inference","created":"2023-06-21","cited_by_count":32,"area":null},{"id":"2205.01500","title":"Meta Learning for Natural Language Processing: A Survey","created":"2022-05-03","cited_by_count":26,"area":null},{"id":"2203.09137","title":"Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning","created":"2022-03-17","cited_by_count":22,"area":null},{"id":"2105.14099","title":"Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning","created":"2021-05-28","cited_by_count":21,"area":null},{"id":"2204.08535","title":"Imagination-Augmented Natural Language Understanding","created":"2022-04-18","cited_by_count":19,"area":null},{"id":"2211.04684","title":"Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind","created":"2022-11-09","cited_by_count":19,"area":null},{"id":"2305.09269","title":"ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification","created":"2023-05-16","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":"2203.14276","title":"Example-based Hypernetworks for Out-of-Distribution Generalization","created":"2022-03-27","cited_by_count":16,"area":null},{"id":"2101.11302","title":"Multilingual and cross-lingual document classification: A meta-learning approach","created":"2021-01-27","cited_by_count":14,"area":null},{"id":"2110.09446","title":"Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learning","created":"2021-10-18","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":"2411.05818","title":"Open LLMs are Necessary for Current Private Adaptations and Outperform their Closed Alternatives","created":"2024-11-02","cited_by_count":12,"area":null},{"id":"2210.12813","title":"TAPE: Assessing Few-shot Russian Language Understanding","created":"2022-10-23","cited_by_count":11,"area":null},{"id":"2106.01051","title":"Minimax and Neyman-Pearson Meta-Learning for Outlier Languages","created":"2021-06-02","cited_by_count":10,"area":null},{"id":"2109.04707","title":"Knowledge-Aware Meta-learning for Low-Resource Text Classification","created":"2021-09-10","cited_by_count":10,"area":null},{"id":"2111.01322","title":"Diverse Distributions of Self-Supervised Tasks for Meta-Learning in NLP","created":"2021-11-02","cited_by_count":10,"area":null},{"id":"2210.10258","title":"Continued Pretraining for Better Zero- and Few-Shot Promptability","created":"2022-10-19","cited_by_count":10,"area":null},{"id":"2304.06136","title":"AGI for Agriculture","created":"2023-04-12","cited_by_count":9,"area":null},{"id":"2201.11576","title":"Grad2Task: Improved Few-shot Text Classification Using Gradients for Task Representation","created":"2022-01-27","cited_by_count":8,"area":null},{"id":"2205.09229","title":"PromptDA: Label-guided Data Augmentation for Prompt-based Few-shot Learners","created":"2022-05-18","cited_by_count":7,"area":null},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2107.09840","title":"Soft Layer Selection with Meta-Learning for Zero-Shot Cross-Lingual Transfer","created":"2021-07-21","cited_by_count":5,"area":null},{"id":"2305.13547","title":"Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot Text Classification Tasks","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2402.13714","title":"An Evaluation of Large Language Models in Bioinformatics Research","created":"2024-02-21","cited_by_count":5,"area":null},{"id":"2207.09157","title":"On the cross-lingual transferability of multilingual prototypical models across NLU tasks","created":"2022-07-19","cited_by_count":4,"area":null},{"id":"2310.16959","title":"Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning","created":"2023-10-25","cited_by_count":4,"area":null},{"id":"2403.15362","title":"CoLLEGe: Concept Embedding Generation for Large Language Models","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2106.02960","title":"Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation","created":"2021-06-05","cited_by_count":2,"area":null},{"id":"2110.06502","title":"Prompt-tuning in ASR systems for efficient domain-adaptation","created":"2021-10-13","cited_by_count":2,"area":null},{"id":"2211.08588","title":"Disentangling Task Relations for Few-shot Text Classification via Self-Supervised Hierarchical Task Clustering","created":"2022-11-16","cited_by_count":2,"area":null},{"id":"2212.00851","title":"SOLD: Sinhala Offensive Language Dataset","created":"2022-12-01","cited_by_count":2,"area":null},{"id":"2404.01822","title":"A (More) Realistic Evaluation Setup for Generalisation of Community Models on Malicious Content Detection","created":"2024-04-02","cited_by_count":1,"area":null},{"id":"2508.03002","title":"Where and How to Enhance: Discovering Bit-Width Contribution for Mixed Precision Quantization","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2605.09027","title":"GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives","created":"2026-05-09","cited_by_count":1,"area":"agents"},{"id":"2102.10760","title":"Unsupervised Meta Learning for One Shot Title Compression in Voice Commerce","created":"2021-02-22","cited_by_count":0,"area":null},{"id":"2210.13979","title":"Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks","created":"2022-10-22","cited_by_count":0,"area":null},{"id":"2210.17437","title":"Learning New Tasks from a Few Examples with Soft-Label Prototypes","created":"2022-10-31","cited_by_count":0,"area":null},{"id":"2211.15195","title":"Distance Metric Learning Loss Functions in Few-Shot Scenarios of Supervised Language Models Fine-Tuning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2211.15202","title":"Revisiting Distance Metric Learning for Few-Shot Natural Language Classification","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2212.01414","title":"Meta-Shop: Improving Item Advertisement For Small Businesses","created":"2022-12-02","cited_by_count":0,"area":null},{"id":"2502.11113","title":"Valuable Hallucinations: Realizable Non-realistic Propositions","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2503.06531","title":"MetaXCR: Reinforcement-Based Meta-Transfer Learning for Cross-Lingual Commonsense Reasoning","created":"2025-03-09","cited_by_count":0,"area":"lr"},{"id":"2510.27675","title":"On the Difficulty of Selecting Few-Shot Examples for Effective LLM-based Vulnerability Detection","created":"2025-10-31","cited_by_count":0,"area":null}],"next_cursor":null}