{"list":"other","total":103,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"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":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2305.20050","title":"Let's Verify Step by Step","created":"2023-05-31","cited_by_count":3789},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1905.02249","title":"MixMatch: A Holistic Approach to Semi-Supervised Learning","created":"2019-05-06","cited_by_count":1391},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"1911.04252","title":"Self-training with Noisy Student improves ImageNet classification","created":"2019-11-11","cited_by_count":1311},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"1804.06872","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","created":"2018-04-18","cited_by_count":1059},{"id":"1610.02242","title":"Temporal Ensembling for Semi-Supervised Learning","created":"2016-10-07","cited_by_count":1057},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1805.12471","title":"Neural Network Acceptability Judgments","created":"2018-05-31","cited_by_count":958},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2002.07394","title":"DivideMix: Learning with Noisy Labels as Semi-supervised Learning","created":"2020-02-18","cited_by_count":692},{"id":"1801.07593","title":"Mitigating Unwanted Biases with Adversarial Learning","created":"2018-01-22","cited_by_count":663},{"id":"2309.00267","title":"RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback","created":"2023-09-01","cited_by_count":625},{"id":"2007.08199","title":"Learning from Noisy Labels with Deep Neural Networks: A Survey","created":"2020-07-16","cited_by_count":582},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"1406.5298","title":"Semi-Supervised Learning with Deep Generative Models","created":"2014-06-20","cited_by_count":496},{"id":"1811.07871","title":"Scalable agent alignment via reward modeling: a research direction","created":"2018-11-19","cited_by_count":447},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1904.01130","title":"PAWS: Paraphrase Adversaries from Word Scrambling","created":"2019-04-01","cited_by_count":402},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2206.05802","title":"Self-critiquing models for assisting human evaluators","created":"2022-06-12","cited_by_count":380},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"1711.10160","title":"Snorkel: Rapid Training Data Creation with Weak Supervision","created":"2017-11-28","cited_by_count":372},{"id":"1808.09121","title":"WiC: the Word-in-Context Dataset for Evaluating Context-Sensitive Meaning Representations","created":"2018-08-28","cited_by_count":372},{"id":"2305.17493","title":"The Curse of Recursion: Training on Generated Data Makes Models Forget","created":"2023-05-27","cited_by_count":356},{"id":"1904.11238","title":"Unsupervised Label Noise Modeling and Loss Correction","created":"2019-04-25","cited_by_count":328},{"id":"1412.6596","title":"Training Deep Neural Networks on Noisy Labels with Bootstrapping","created":"2014-12-20","cited_by_count":322},{"id":"1810.01943","title":"AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias","created":"2018-10-03","cited_by_count":319},{"id":"2004.06100","title":"Pretrained Transformers Improve Out-of-Distribution Robustness","created":"2020-04-13","cited_by_count":294},{"id":"2109.10862","title":"Recursively Summarizing Books with Human Feedback","created":"2021-09-22","cited_by_count":290},{"id":"1909.00277","title":"Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning","created":"2019-08-31","cited_by_count":285},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"1906.01820","title":"Risks from Learned Optimization in Advanced Machine Learning Systems","created":"2019-06-05","cited_by_count":258},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2006.13554","title":"Normalized Loss Functions for Deep Learning with Noisy Labels","created":"2020-06-24","cited_by_count":257},{"id":"2211.03540","title":"Measuring Progress on Scalable Oversight for Large Language Models","created":"2022-11-04","cited_by_count":225},{"id":"1805.12317","title":"Multiaccuracy: Black-Box Post-Processing for Fairness in Classification","created":"2018-05-31","cited_by_count":222},{"id":"1802.05300","title":"Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise","created":"2018-02-14","cited_by_count":216},{"id":"1802.08735","title":"A DIRT-T Approach to Unsupervised Domain Adaptation","created":"2018-02-23","cited_by_count":215},{"id":"1903.07788","title":"Probabilistic End-to-end Noise Correction for Learning with Noisy Labels","created":"2019-03-19","cited_by_count":210},{"id":"2011.12945","title":"No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems","created":"2020-11-25","cited_by_count":209},{"id":"2306.09479","title":"Inverse Scaling: When Bigger Isn't Better","created":"2023-06-15","cited_by_count":207},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205},{"id":"1511.01432","title":"Semi-supervised Sequence Learning","created":"2015-11-04","cited_by_count":198},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190},{"id":"2010.03622","title":"Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data","created":"2020-10-07","cited_by_count":180},{"id":"1902.00164","title":"DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension","created":"2019-02-01","cited_by_count":156},{"id":"1704.01444","title":"Learning to Generate Reviews and Discovering Sentiment","created":"2017-04-05","cited_by_count":148},{"id":"1810.08575","title":"Supervising strong learners by amplifying weak experts","created":"2018-10-19","cited_by_count":145},{"id":"1808.01097","title":"CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images","created":"2018-08-03","cited_by_count":126},{"id":"1909.03065","title":"\"Going on a vacation\" takes longer than \"Going for a walk\": A Study of Temporal Commonsense Understanding","created":"2019-09-06","cited_by_count":123},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113},{"id":"2311.09677","title":"R-Tuning: Instructing Large Language Models to Say `I Don't Know'","created":"2023-11-16","cited_by_count":111},{"id":"2311.08379","title":"Scheming AIs: Will AIs fake alignment during training in order to get power?","created":"2023-11-14","cited_by_count":97},{"id":"1909.03553","title":"QuaRTz: An Open-Domain Dataset of Qualitative Relationship Questions","created":"2019-09-08","cited_by_count":89},{"id":"2309.15840","title":"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions","created":"2023-09-26","cited_by_count":83},{"id":"2006.10032","title":"Self-training Avoids Using Spurious Features Under Domain Shift","created":"2020-06-17","cited_by_count":69},{"id":"2112.01008","title":"Editing a classifier by rewriting its prediction rules","created":"2021-12-02","cited_by_count":65},{"id":"2202.03418","title":"Diversify and Disambiguate: Learning From Underspecified Data","created":"2022-02-07","cited_by_count":56},{"id":"1703.00854","title":"Learning the Structure of Generative Models without Labeled Data","created":"2017-03-02","cited_by_count":50},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23},{"id":"1902.09469","title":"Embedded Agency","created":"2019-02-25","cited_by_count":19}],"next_cursor":"100"}