{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"2302.04023","title":"A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity","created":"2023-02-08","cited_by_count":894},{"id":"1901.11196","title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks","created":"2019-01-31","cited_by_count":807},{"id":"1511.06709","title":"Improving Neural Machine Translation Models with Monolingual Data","created":"2015-11-20","cited_by_count":788},{"id":"2301.13688","title":"The Flan Collection: Designing Data and Methods for Effective Instruction Tuning","created":"2023-01-31","cited_by_count":739},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"2302.06476","title":"Is ChatGPT a General-Purpose Natural Language Processing Task Solver?","created":"2023-02-08","cited_by_count":488},{"id":"2111.01243","title":"Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey","created":"2021-11-01","cited_by_count":463},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"2105.03075","title":"A Survey of Data Augmentation Approaches for NLP","created":"2021-05-07","cited_by_count":409},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"2301.13867","title":"Mathematical Capabilities of ChatGPT","created":"2023-01-31","cited_by_count":268},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"1805.06201","title":"Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations","created":"2018-05-16","cited_by_count":201},{"id":"1907.06616","title":"Facebook FAIR's WMT19 News Translation Task Submission","created":"2019-07-15","cited_by_count":179},{"id":"2003.02245","title":"Data Augmentation using Pre-trained Transformer Models","created":"2020-03-04","cited_by_count":168},{"id":"1603.00892","title":"Counter-fitting Word Vectors to Linguistic Constraints","created":"2016-03-02","cited_by_count":140},{"id":"2302.07257","title":"ChatCAD: Interactive Computer-Aided Diagnosis on Medical Image using Large Language Models","created":"2023-02-14","cited_by_count":116},{"id":"2107.03158","title":"A Survey on Data Augmentation for Text Classification","created":"2021-07-07","cited_by_count":111},{"id":"2212.09292","title":"ChatGPT: The End of Online Exam Integrity?","created":"2022-12-19","cited_by_count":88},{"id":"1908.06039","title":"Few-shot Text Classification with Distributional Signatures","created":"2019-08-16","cited_by_count":58},{"id":"1910.04176","title":"A Closer Look At Feature Space Data Augmentation For Few-Shot Intent Classification","created":"2019-10-09","cited_by_count":45},{"id":"2106.09362","title":"Frustratingly Easy Transferability Estimation","created":"2021-06-17","cited_by_count":45},{"id":"2007.09604","title":"Meta-learning for Few-shot Natural Language Processing: A Survey","created":"2020-07-19","cited_by_count":42},{"id":"2302.04335","title":"Will ChatGPT get you caught? Rethinking of Plagiarism Detection","created":"2023-02-08","cited_by_count":41},{"id":"1812.04718","title":"Text Data Augmentation Made Simple By Leveraging NLP Cloud APIs","created":"2018-12-05","cited_by_count":40},{"id":"2103.07552","title":"Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning","created":"2021-03-12","cited_by_count":35},{"id":"2201.06494","title":"AugLy: Data Augmentations for Robustness","created":"2022-01-17","cited_by_count":34},{"id":"1809.02079","title":"Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Models","created":"2018-09-06","cited_by_count":26},{"id":"2205.01500","title":"Meta Learning for Natural Language Processing: A Survey","created":"2022-05-03","cited_by_count":26},{"id":"2302.10447","title":"Mask-guided BERT for Few Shot Text Classification","created":"2023-02-21","cited_by_count":25},{"id":"2205.05313","title":"Towards Unified Prompt Tuning for Few-shot Text Classification","created":"2022-05-11","cited_by_count":18},{"id":"2104.06669","title":"NAREOR: The Narrative Reordering Problem","created":"2021-04-14","cited_by_count":14},{"id":"2204.14081","title":"Few-shot learning for medical text: A systematic review","created":"2022-04-21","cited_by_count":13}],"next_cursor":null}