{"list":"other","total":51,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2206.14858","title":"Solving Quantitative Reasoning Problems with Language Models","created":"2022-06-29","cited_by_count":1392},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2205.14217","title":"Diffusion-LM Improves Controllable Text Generation","created":"2022-05-27","cited_by_count":1027},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"1607.01759","title":"Bag of Tricks for Efficient Text Classification","created":"2016-07-06","cited_by_count":876},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"1909.01326","title":"The Woman Worked as a Babysitter: On Biases in Language Generation","created":"2019-09-03","cited_by_count":541},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"1903.04561","title":"Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification","created":"2019-03-11","cited_by_count":404},{"id":"2001.00973","title":"Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing","created":"2020-01-03","cited_by_count":384},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"1612.03651","title":"FastText.zip: Compressing text classification models","created":"2016-12-12","cited_by_count":335},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234},{"id":"1907.12461","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","created":"2019-07-29","cited_by_count":182},{"id":"2202.11705","title":"COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics","created":"2022-02-23","cited_by_count":161},{"id":"1809.10610","title":"Counterfactual Fairness in Text Classification through Robustness","created":"2018-09-27","cited_by_count":151},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107},{"id":"2202.12299","title":"Capturing Failures of Large Language Models via Human Cognitive Biases","created":"2022-02-24","cited_by_count":98},{"id":"2102.04509","title":"Oops I Took A Gradient: Scalable Sampling for Discrete Distributions","created":"2021-02-08","cited_by_count":92},{"id":"2108.01850","title":"Controlled Text Generation as Continuous Optimization with Multiple Constraints","created":"2021-08-04","cited_by_count":70},{"id":"1801.03604","title":"Conversational AI: The Science Behind the Alexa Prize","created":"2018-01-11","cited_by_count":63},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60},{"id":"2010.02510","title":"Investigating African-American Vernacular English in Transformer-Based Text Generation","created":"2020-10-06","cited_by_count":53},{"id":"2206.09914","title":"A Langevin-like Sampler for Discrete Distributions","created":"2022-06-20","cited_by_count":44},{"id":"1809.08352","title":"Unrestricted Adversarial Examples","created":"2018-09-22","cited_by_count":40},{"id":"2111.08267","title":"Solving Probability and Statistics Problems by Program Synthesis","created":"2021-11-16","cited_by_count":9},{"id":"2208.04417","title":"Debiased Large Language Models Still Associate Muslims with Uniquely Violent Acts","created":"2022-08-08","cited_by_count":8}],"next_cursor":null}