{"list":"other","total":68,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"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":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"2004.09456","title":"StereoSet: Measuring stereotypical bias in pretrained language models","created":"2020-04-20","cited_by_count":924},{"id":"2005.10243","title":"What Makes for Good Views for Contrastive Learning?","created":"2020-05-20","cited_by_count":846},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2308.08747","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","created":"2023-08-17","cited_by_count":639},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"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":"1609.02943","title":"Stealing Machine Learning Models via Prediction APIs","created":"2016-09-09","cited_by_count":619},{"id":"1905.12616","title":"Defending Against Neural Fake News","created":"2019-05-29","cited_by_count":559},{"id":"2011.03395","title":"Underspecification Presents Challenges for Credibility in Modern Machine Learning","created":"2020-11-06","cited_by_count":496},{"id":"1707.09457","title":"Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints","created":"2017-07-29","cited_by_count":420},{"id":"2002.06305","title":"Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stopping","created":"2020-02-15","cited_by_count":384},{"id":"2304.05335","title":"Toxicity in ChatGPT: Analyzing Persona-assigned Language Models","created":"2023-04-11","cited_by_count":360},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"2106.13219","title":"Towards Understanding and Mitigating Social Biases in Language Models","created":"2021-06-24","cited_by_count":296},{"id":"1906.08976","title":"Mitigating Gender Bias in Natural Language Processing: Literature Review","created":"2019-06-21","cited_by_count":287},{"id":"1801.01944","title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text","created":"2018-01-05","cited_by_count":274},{"id":"2303.11408","title":"Stable Bias: Analyzing Societal Representations in Diffusion Models","created":"2023-03-20","cited_by_count":226},{"id":"2307.14324","title":"Evaluating the Moral Beliefs Encoded in LLMs","created":"2023-07-26","cited_by_count":215},{"id":"1911.05248","title":"What Do Compressed Deep Neural Networks Forget?","created":"2019-11-13","cited_by_count":171},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"1707.00075","title":"Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations","created":"2017-07-01","cited_by_count":165},{"id":"2204.07931","title":"On the Origin of Hallucinations in Conversational Models: Is it the Datasets or the Models?","created":"2022-04-17","cited_by_count":138},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136},{"id":"2005.03642","title":"On Exposure Bias, Hallucination and Domain Shift in Neural Machine Translation","created":"2020-05-07","cited_by_count":127},{"id":"1908.08843","title":"Fairness in Deep Learning: A Computational Perspective","created":"2019-08-23","cited_by_count":123},{"id":"2302.08081","title":"Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarization","created":"2023-02-16","cited_by_count":122},{"id":"1809.02208","title":"Assessing Gender Bias in Machine Translation -- A Case Study with Google Translate","created":"2018-09-06","cited_by_count":121},{"id":"1805.08841","title":"Distribution Matching Losses Can Hallucinate Features in Medical Image Translation","created":"2018-05-22","cited_by_count":99},{"id":"2002.03206","title":"Characterizing Structural Regularities of Labeled Data in Overparameterized Models","created":"2020-02-08","cited_by_count":93},{"id":"1906.06629","title":"Robust Federated Learning in a Heterogeneous Environment","created":"2019-06-16","cited_by_count":90},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87},{"id":"1901.02547","title":"Problem Formulation and Fairness","created":"2019-01-08","cited_by_count":85},{"id":"2310.07251","title":"Ethical Reasoning over Moral Alignment: A Case and Framework for In-Context Ethical Policies in LLMs","created":"2023-10-11","cited_by_count":64},{"id":"1801.03421","title":"Blessing of dimensionality: mathematical foundations of the statistical physics of data","created":"2018-01-10","cited_by_count":55},{"id":"2305.11844","title":"AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asia","created":"2023-05-19","cited_by_count":54},{"id":"2004.12764","title":"\"Call me sexist, but...\": Revisiting Sexism Detection Using Psychological Scales and Adversarial Samples","created":"2020-04-27","cited_by_count":48},{"id":"2205.13574","title":"Pruning has a disparate impact on model accuracy","created":"2022-05-26","cited_by_count":44},{"id":"2312.10075","title":"Assessing LLMs for Moral Value Pluralism","created":"2023-12-08","cited_by_count":34},{"id":"2310.00158","title":"Feedback-guided Data Synthesis for Imbalanced Classification","created":"2023-09-29","cited_by_count":33},{"id":"2012.02775","title":"Representation Based Complexity Measures for Predicting Generalization in Deep Learning","created":"2020-12-04","cited_by_count":29},{"id":"2307.04138","title":"On The Impact of Machine Learning Randomness on Group Fairness","created":"2023-07-09","cited_by_count":26},{"id":"2304.03935","title":"Last-Layer Fairness Fine-tuning is Simple and Effective for Neural Networks","created":"2023-04-08","cited_by_count":17},{"id":"2310.11867","title":"Evaluating the Fairness of Discriminative Foundation Models in Computer Vision","created":"2023-10-18","cited_by_count":12},{"id":"2106.06955","title":"Towards Understanding Iterative Magnitude Pruning: Why Lottery Tickets Win","created":"2021-06-13","cited_by_count":11},{"id":"2011.01307","title":"The Mathematical Foundations of Manifold Learning","created":"2020-10-30","cited_by_count":7},{"id":"2310.20673","title":"Balancing Act: Constraining Disparate Impact in Sparse Models","created":"2023-10-31","cited_by_count":7},{"id":"2311.14859","title":"An Empirical Investigation into Benchmarking Model Multiplicity for Trustworthy Machine Learning: A Case Study on Image Classification","created":"2023-11-24","cited_by_count":7},{"id":"2310.17530","title":"Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models","created":"2023-10-26","cited_by_count":6},{"id":"2405.19272","title":"Differentially Private Clustered Federated Learning","created":"2024-05-29","cited_by_count":4},{"id":"2306.10043","title":"Unraveling the Interconnected Axes of Heterogeneity in Machine Learning for Democratic and Inclusive Advancements","created":"2023-06-11","cited_by_count":2},{"id":"2309.02550","title":"Tidying Up the Conversational Recommender Systems' Biases","created":"2023-09-05","cited_by_count":1}],"next_cursor":null}