{"list":"other","total":127,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"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":"2009.01325","title":"Learning to summarize from human feedback","created":"2020-09-02","cited_by_count":2588},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"1908.09635","title":"A Survey on Bias and Fairness in Machine Learning","created":"2019-08-23","cited_by_count":1917},{"id":"2210.09261","title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","created":"2022-10-17","cited_by_count":1807},{"id":"1905.00537","title":"SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems","created":"2019-05-02","cited_by_count":1729},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1803.09010","title":"Datasheets for Datasets","created":"2018-03-23","cited_by_count":1386},{"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":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"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":"2109.00859","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","created":"2021-09-02","cited_by_count":906},{"id":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"1910.14599","title":"Adversarial NLI: A New Benchmark for Natural Language Understanding","created":"2019-10-31","cited_by_count":807},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2301.10226","title":"A Watermark for Large Language Models","created":"2023-01-24","cited_by_count":725},{"id":"2010.00133","title":"CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models","created":"2020-09-30","cited_by_count":710},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"1909.01326","title":"The Woman Worked as a Babysitter: On Biases in Language Generation","created":"2019-09-03","cited_by_count":541},{"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":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"2001.09977","title":"Towards a Human-like Open-Domain Chatbot","created":"2020-01-27","cited_by_count":470},{"id":"2104.14337","title":"Dynabench: Rethinking Benchmarking in NLP","created":"2021-04-07","cited_by_count":459},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"1903.10561","title":"On Measuring Social Biases in Sentence Encoders","created":"2019-03-25","cited_by_count":398},{"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":"2005.12833","title":"Med-BERT: pre-trained contextualized embeddings on large-scale structured electronic health records for disease prediction","created":"2020-05-22","cited_by_count":373},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"2004.01970","title":"BAE: BERT-based Adversarial Examples for Text Classification","created":"2020-04-04","cited_by_count":316},{"id":"1912.05511","title":"Measurement and Fairness","created":"2019-12-11","cited_by_count":308},{"id":"2111.07997","title":"Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection","created":"2021-11-15","cited_by_count":264},{"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":"2103.12028","title":"Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets","created":"2021-03-22","cited_by_count":243},{"id":"2111.02840","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","created":"2021-11-04","cited_by_count":232},{"id":"2010.06032","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","created":"2020-10-12","cited_by_count":224},{"id":"2012.15606","title":"HateCheck: Functional Tests for Hate Speech Detection Models","created":"2020-12-31","cited_by_count":216},{"id":"2202.07785","title":"Predictability and Surprise in Large Generative Models","created":"2022-02-15","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":"2204.01075","title":"Data Cards: Purposeful and Transparent Dataset Documentation for Responsible AI","created":"2022-04-03","cited_by_count":171},{"id":"2109.07445","title":"Challenges in Detoxifying Language Models","created":"2021-09-15","cited_by_count":169},{"id":"2302.03494","title":"A Categorical Archive of ChatGPT Failures","created":"2023-02-06","cited_by_count":168},{"id":"2004.07213","title":"Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims","created":"2020-04-15","cited_by_count":165},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163},{"id":"2102.02503","title":"Understanding the Capabilities, Limitations, and Societal Impact of Large Language Models","created":"2021-02-04","cited_by_count":160},{"id":"1811.05577","title":"Aequitas: A Bias and Fairness Audit Toolkit","created":"2018-11-14","cited_by_count":147},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141},{"id":"2210.05791","title":"Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction","created":"2022-10-11","cited_by_count":138},{"id":"1906.06668","title":"Principles alone cannot guarantee ethical AI","created":"2019-06-16","cited_by_count":135},{"id":"1912.10389","title":"Lessons from Archives: Strategies for Collecting Sociocultural Data in Machine Learning","created":"2019-12-22","cited_by_count":116},{"id":"2110.06674","title":"Truthful AI: Developing and governing AI that does not lie","created":"2021-10-13","cited_by_count":113},{"id":"2101.04840","title":"Robustness Gym: Unifying the NLP Evaluation Landscape","created":"2021-01-13","cited_by_count":108},{"id":"2302.02337","title":"Regulating ChatGPT and other Large Generative AI Models","created":"2023-02-05","cited_by_count":104},{"id":"2206.09511","title":"The Fallacy of AI Functionality","created":"2022-06-20","cited_by_count":88},{"id":"2206.00761","title":"On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting","created":"2022-06-01","cited_by_count":82},{"id":"2105.02732","title":"What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus","created":"2021-05-06","cited_by_count":80},{"id":"1710.07395","title":"Detecting Online Hate Speech Using Context Aware Models","created":"2017-10-20","cited_by_count":72},{"id":"2206.04737","title":"Outsider Oversight: Designing a Third Party Audit Ecosystem for AI Governance","created":"2022-06-09","cited_by_count":67},{"id":"2106.04511","title":"Designing Toxic Content Classification for a Diversity of Perspectives","created":"2021-06-04","cited_by_count":65},{"id":"2207.07180","title":"Contrastive Adapters for Foundation Model Group Robustness","created":"2022-07-14","cited_by_count":62},{"id":"2209.00731","title":"In conversation with Artificial Intelligence: aligning language models with human values","created":"2022-09-01","cited_by_count":62},{"id":"2205.02894","title":"Interactive Model Cards: A Human-Centered Approach to Model Documentation","created":"2022-05-05","cited_by_count":61},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60},{"id":"2108.05921","title":"Hatemoji: A Test Suite and Adversarially-Generated Dataset for Benchmarking and Detecting Emoji-based Hate","created":"2021-08-12","cited_by_count":50},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49},{"id":"2011.03116","title":"Behavioral Use Licensing for Responsible AI","created":"2020-11-04","cited_by_count":46},{"id":"2204.14256","title":"Handling and Presenting Harmful Text in NLP Research","created":"2022-04-29","cited_by_count":43},{"id":"1602.07043","title":"Auditing Black-box Models for Indirect Influence","created":"2016-02-23","cited_by_count":41},{"id":"2103.04044","title":"Putting Humans in the Natural Language Processing Loop: A Survey","created":"2021-03-06","cited_by_count":40},{"id":"2207.02852","title":"Machine Learning Model Sizes and the Parameter Gap","created":"2022-07-05","cited_by_count":39},{"id":"1707.07232","title":"Society-in-the-Loop: Programming the Algorithmic Social Contract","created":"2017-07-23","cited_by_count":35},{"id":"2206.03216","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","created":"2022-05-04","cited_by_count":33}],"next_cursor":"100"}