{"list":"other","total":52,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"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":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2107.06499","title":"Deduplicating Training Data Makes Language Models Better","created":"2021-07-14","cited_by_count":714},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"1711.05144","title":"Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness","created":"2017-11-14","cited_by_count":384},{"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":"2101.05783","title":"Persistent Anti-Muslim Bias in Large Language Models","created":"2021-01-14","cited_by_count":377},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"1711.08412","title":"Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypes","created":"2017-11-22","cited_by_count":253},{"id":"2006.16923","title":"Large image datasets: A pyrrhic win for computer vision?","created":"2020-06-24","cited_by_count":237},{"id":"1803.09797","title":"Women also Snowboard: Overcoming Bias in Captioning Models","created":"2018-03-26","cited_by_count":236},{"id":"1806.02847","title":"A Simple Method for Commonsense Reasoning","created":"2018-06-07","cited_by_count":223},{"id":"1802.04422","title":"A comparative study of fairness-enhancing interventions in machine learning","created":"2018-02-13","cited_by_count":208},{"id":"1512.00596","title":"The MegaFace Benchmark: 1 Million Faces for Recognition at Scale","created":"2015-12-02","cited_by_count":200},{"id":"2005.00813","title":"Social Biases in NLP Models as Barriers for Persons with Disabilities","created":"2020-05-02","cited_by_count":182},{"id":"2204.01075","title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","created":"2022-04-03","cited_by_count":171},{"id":"1711.08536","title":"No Classification without Representation: Assessing Geodiversity Issues in Open Data Sets for the Developing World","created":"2017-11-22","cited_by_count":153},{"id":"1911.03064","title":"Reducing Sentiment Bias in Language Models via Counterfactual Evaluation","created":"2019-11-08","cited_by_count":148},{"id":"1811.05577","title":"Aequitas: A Bias and Fairness Audit Toolkit","created":"2018-11-14","cited_by_count":147},{"id":"2010.13561","title":"Towards Accountability for Machine Learning Datasets: Practices from Software Engineering and Infrastructure","created":"2020-10-23","cited_by_count":138},{"id":"2310.20707","title":"What's In My Big Data?","created":"2023-10-31","cited_by_count":129},{"id":"1812.06469","title":"The Adverse Effects of Code Duplication in Machine Learning Models of Code","created":"2018-12-16","cited_by_count":126},{"id":"1912.03593","title":"Towards a Critical Race Methodology in Algorithmic Fairness","created":"2019-12-08","cited_by_count":125},{"id":"2101.09995","title":"Re-imagining Algorithmic Fairness in India and Beyond","created":"2021-01-25","cited_by_count":104},{"id":"2001.00964","title":"Saving Face: Investigating the Ethical Concerns of Facial Recognition Auditing","created":"2020-01-03","cited_by_count":89},{"id":"1902.11097","title":"Predictive Inequity in Object Detection","created":"2019-02-21","cited_by_count":77},{"id":"2206.08931","title":"CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation","created":"2022-06-09","cited_by_count":59},{"id":"2105.05241","title":"Addressing \"Documentation Debt\" in Machine Learning Research: A Retrospective Datasheet for BookCorpus","created":"2021-05-11","cited_by_count":47},{"id":"2007.00049","title":"OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings","created":"2020-06-30","cited_by_count":40},{"id":"2206.02923","title":"Understanding Machine Learning Practitioners' Data Documentation Perceptions, Needs, Challenges, and Desiderata","created":"2022-06-06","cited_by_count":28},{"id":"2211.14611","title":"The Principles of Data-Centric AI (DCAI)","created":"2022-11-26","cited_by_count":26},{"id":"2006.04707","title":"Principles to Practices for Responsible AI: Closing the Gap","created":"2020-06-08","cited_by_count":25},{"id":"2101.03827","title":"Representativeness in Statistics, Politics, and Machine Learning","created":"2021-01-11","cited_by_count":17},{"id":"2103.09058","title":"Understanding the Representation and Representativeness of Age in AI Data Sets","created":"2021-03-10","cited_by_count":15},{"id":"2205.05306","title":"The Conflict Between Explainable and Accountable Decision-Making Algorithms","created":"2022-05-11","cited_by_count":13},{"id":"2112.03529","title":"Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets","created":"2021-12-07","cited_by_count":11},{"id":"2010.06041","title":"Towards Machine Translation for the Kurdish Language","created":"2020-10-12","cited_by_count":6},{"id":"2111.08723","title":"Who Decides if AI is Fair? The Labels Problem in Algorithmic Auditing","created":"2021-11-16","cited_by_count":2}],"next_cursor":null}