{"list":"other","total":56,"rows":[{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"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":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1704.05426","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","created":"2017-04-18","cited_by_count":2682},{"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},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2104.08786","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","created":"2021-04-18","cited_by_count":1135},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"2001.07676","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","created":"2020-01-21","cited_by_count":938},{"id":"1911.00536","title":"DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation","created":"2019-11-01","cited_by_count":842},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2106.11520","title":"BARTScore: Evaluating Generated Text as Text Generation","created":"2021-06-22","cited_by_count":722},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"1912.00049","title":"Square Attack: a query-efficient black-box adversarial attack via random search","created":"2019-11-29","cited_by_count":685},{"id":"2009.07118","title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","created":"2020-09-15","cited_by_count":669},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"1804.08598","title":"Black-box Adversarial Attacks with Limited Queries and Information","created":"2018-04-23","cited_by_count":501},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2104.06599","title":"Learning How to Ask: Querying LMs with Mixtures of Soft Prompts","created":"2021-04-14","cited_by_count":377},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"1808.09602","title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","created":"2018-08-29","cited_by_count":322},{"id":"2104.05240","title":"Factual Probing Is [MASK]: Learning vs. Learning to Recall","created":"2021-04-12","cited_by_count":291},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1905.07121","title":"Simple Black-box Adversarial Attacks","created":"2019-05-17","cited_by_count":251},{"id":"2105.11259","title":"PTR: Prompt Tuning with Rules for Text Classification","created":"2021-05-24","cited_by_count":238},{"id":"2110.07904","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","created":"2021-10-15","cited_by_count":235},{"id":"2101.00121","title":"WARP: Word-level Adversarial ReProgramming","created":"2021-01-01","cited_by_count":221},{"id":"1909.00505","title":"Commonsense Knowledge Mining from Pretrained Models","created":"2019-09-02","cited_by_count":189},{"id":"1903.05987","title":"To Tune or Not to Tune? Adapting Pretrained Representations to Diverse Tasks","created":"2019-03-14","cited_by_count":167},{"id":"1807.07978","title":"Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors","created":"2018-07-20","cited_by_count":146},{"id":"1910.12366","title":"Thieves on Sesame Street! Model Extraction of BERT-based APIs","created":"2019-10-27","cited_by_count":139},{"id":"2008.05122","title":"The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models","created":"2020-08-12","cited_by_count":125},{"id":"1710.06071","title":"PubMed 200k RCT: a Dataset for Sequential Sentence Classification in Medical Abstracts","created":"2017-10-17","cited_by_count":124},{"id":"2104.14690","title":"Entailment as Few-Shot Learner","created":"2021-04-29","cited_by_count":123},{"id":"1906.06919","title":"Improving Black-box Adversarial Attacks with a Transfer-based Prior","created":"2019-06-17","cited_by_count":121},{"id":"2103.05327","title":"BERTese: Learning to Speak to BERT","created":"2021-03-09","cited_by_count":82},{"id":"2102.12206","title":"PADA: Example-based Prompt Learning for on-the-fly Adaptation to Unseen Domains","created":"2021-02-24","cited_by_count":61},{"id":"1911.07140","title":"Black-Box Adversarial Attack with Transferable Model-based Embedding","created":"2019-11-17","cited_by_count":57},{"id":"2104.01539","title":"DINE: Domain Adaptation from Single and Multiple Black-box Predictors","created":"2021-04-04","cited_by_count":51},{"id":"2106.03310","title":"Zero-Shot Knowledge Distillation from a Decision-Based Black-Box Model","created":"2021-06-07","cited_by_count":37},{"id":"1911.00720","title":"ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations","created":"2019-11-02","cited_by_count":35},{"id":"2111.05685","title":"Efficient Neural Network Training via Forward and Backward Propagation Sparsification","created":"2021-11-10","cited_by_count":30},{"id":"2006.10680","title":"DisARM: An Antithetic Gradient Estimator for Binary Latent Variables","created":"2020-06-18","cited_by_count":28},{"id":"2010.02569","title":"StyleDGPT: Stylized Response Generation with Pre-trained Language Models","created":"2020-10-06","cited_by_count":10}],"next_cursor":null}