{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"1508.05326","title":"A large annotated corpus for learning natural language inference","created":"2015-08-21","cited_by_count":1847},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"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":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1707.07328","title":"Adversarial Examples for Evaluating Reading Comprehension Systems","created":"2017-07-23","cited_by_count":571},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2310.18018","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark","created":"2023-10-27","cited_by_count":348},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2103.09177","title":"Deep learning: a statistical viewpoint","created":"2021-03-16","cited_by_count":240},{"id":"2102.01672","title":"The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics","created":"2021-02-02","cited_by_count":239},{"id":"2203.08242","title":"Data Contamination: From Memorization to Exploitation","created":"2022-03-15","cited_by_count":236},{"id":"2402.03927","title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","created":"2024-02-06","cited_by_count":229},{"id":"1904.03035","title":"Identifying and Reducing Gender Bias in Word-Level Language Models","created":"2019-04-05","cited_by_count":214},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207},{"id":"2104.02145","title":"What Will it Take to Fix Benchmarking in Natural Language Understanding?","created":"2021-04-05","cited_by_count":203},{"id":"1904.04047","title":"Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings","created":"2019-04-03","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":"2302.08500","title":"Auditing large language models: a three-layered approach","created":"2023-02-16","cited_by_count":137},{"id":"2209.06640","title":"Revisiting Neural Scaling Laws in Language and Vision","created":"2022-09-13","cited_by_count":132},{"id":"2101.04719","title":"Expanding Explainability: Towards Social Transparency in AI systems","created":"2021-01-12","cited_by_count":124},{"id":"1502.04585","title":"The Ladder: A Reliable Leaderboard for Machine Learning Competitions","created":"2015-02-16","cited_by_count":69},{"id":"2205.02894","title":"Interactive Model Cards: A Human-Centered Approach to Model Documentation","created":"2022-05-05","cited_by_count":61},{"id":"2311.03449","title":"Into the LAIONs Den: Investigating Hate in Multimodal Datasets","created":"2023-11-06","cited_by_count":54},{"id":"2303.02552","title":"An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registry","created":"2023-03-05","cited_by_count":47},{"id":"2011.03116","title":"Behavioral Use Licensing for Responsible AI","created":"2020-11-04","cited_by_count":46},{"id":"2312.06420","title":"Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It","created":"2023-12-11","cited_by_count":44},{"id":"2310.07879","title":"Deepfakes, Phrenology, Surveillance, and More! A Taxonomy of AI Privacy Risks","created":"2023-10-11","cited_by_count":31},{"id":"2105.03322","title":"Are Pre-trained Convolutions Better than Pre-trained Transformers?","created":"2021-05-07","cited_by_count":27},{"id":"2401.13822","title":"Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on Hugging Face","created":"2024-01-24","cited_by_count":27},{"id":"2406.13843","title":"Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data","created":"2024-06-19","cited_by_count":20},{"id":"2405.13058","title":"The AI Community Building the Future? A Quantitative Analysis of Development Activity on Hugging Face Hub","created":"2024-05-20","cited_by_count":18},{"id":"2405.10799","title":"Training Compute Thresholds: Features and Functions in AI Regulation","created":"2024-05-17","cited_by_count":14},{"id":"2102.13189","title":"Rip van Winkle's Razor: A Simple Estimate of Overfit to Test Data","created":"2021-02-25","cited_by_count":8},{"id":"2307.14841","title":"On the Suitability of Hugging Face Hub for Empirical Studies","created":"2023-07-27","cited_by_count":8},{"id":"2303.08934","title":"PTMTorrent: A Dataset for Mining Open-source Pre-trained Model Packages","created":"2023-03-15","cited_by_count":7},{"id":"2402.05979","title":"On the Standardization of Behavioral Use Clauses and Their Adoption for Responsible Licensing of AI","created":"2024-02-07","cited_by_count":7},{"id":"2402.07323","title":"Lessons Learned from Mining the Hugging Face Repository","created":"2024-02-11","cited_by_count":7},{"id":"1706.02733","title":"Climbing a shaky ladder: Better adaptive risk estimation","created":"2017-06-08","cited_by_count":6},{"id":"2309.14245","title":"Do We Run How We Say We Run? Formalization and Practice of Governance in OSS Communities","created":"2023-09-25","cited_by_count":3},{"id":"2203.03144","title":"Open Source Software Sustainability: Combining Institutional Analysis and Socio-Technical Networks","created":"2022-03-07","cited_by_count":2},{"id":"2310.03620","title":"PeaTMOSS: Mining Pre-Trained Models in Open-Source Software","created":"2023-10-05","cited_by_count":1}],"next_cursor":null}