{"list":"other","total":89,"rows":[{"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":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"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":"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":"1906.02243","title":"Energy and Policy Considerations for Deep Learning in NLP","created":"2019-06-05","cited_by_count":1254},{"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":"1608.07187","title":"Semantics derived automatically from language corpora contain human-like biases","created":"2016-08-25","cited_by_count":901},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"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":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"1910.09700","title":"Quantifying the Carbon Emissions of Machine Learning","created":"2019-10-21","cited_by_count":521},{"id":"1908.09203","title":"Release Strategies and the Social Impacts of Language Models","created":"2019-08-24","cited_by_count":513},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2303.11156","title":"Can AI-Generated Text be Reliably Detected?","created":"2023-03-17","cited_by_count":386},{"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":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"1905.12101","title":"Differential Privacy Has Disparate Impact on Model Accuracy","created":"2019-05-28","cited_by_count":316},{"id":"2211.02001","title":"Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model","created":"2022-11-03","cited_by_count":265},{"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":"2002.05651","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","created":"2020-01-31","cited_by_count":249},{"id":"2111.00364","title":"Sustainable AI: Environmental Implications, Challenges and Opportunities","created":"2021-10-30","cited_by_count":242},{"id":"1905.12516","title":"Racial Bias in Hate Speech and Abusive Language Detection Datasets","created":"2019-05-29","cited_by_count":209},{"id":"2302.04222","title":"Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models","created":"2023-02-08","cited_by_count":205},{"id":"1904.03310","title":"Gender Bias in Contextualized Word Embeddings","created":"2019-04-05","cited_by_count":203},{"id":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195},{"id":"2106.10328","title":"Process for Adapting Language Models to Society (PALMS) with Values-Targeted Datasets","created":"2021-06-18","cited_by_count":181},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"2301.04246","title":"Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigations","created":"2023-01-10","cited_by_count":158},{"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":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2210.05791","title":"Sociotechnical Harms of Algorithmic Systems: Scoping a Taxonomy for Harm Reduction","created":"2022-10-11","cited_by_count":138},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135},{"id":"2010.02428","title":"UnQovering Stereotyping Biases via Underspecified Questions","created":"2020-10-06","cited_by_count":126},{"id":"2110.05699","title":"On Releasing Annotator-Level Labels and Information in Datasets","created":"2021-10-12","cited_by_count":126},{"id":"1705.09899","title":"Understanding Abuse: A Typology of Abusive Language Detection Subtasks","created":"2017-05-28","cited_by_count":116},{"id":"2104.06390","title":"Detoxifying Language Models Risks Marginalizing Minority Voices","created":"2021-04-13","cited_by_count":107},{"id":"2101.09995","title":"Re-imagining Algorithmic Fairness in India and Beyond","created":"2021-01-25","cited_by_count":104},{"id":"1811.10104","title":"50 Years of Test (Un)fairness: Lessons for Machine Learning","created":"2018-11-25","cited_by_count":101},{"id":"2007.04068","title":"Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligence","created":"2020-07-08","cited_by_count":101},{"id":"2004.08900","title":"The Cost of Training NLP Models: A Concise Overview","created":"2020-04-19","cited_by_count":98},{"id":"1909.10705","title":"Do Massively Pretrained Language Models Make Better Storytellers?","created":"2019-09-24","cited_by_count":90},{"id":"2108.04308","title":"Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development","created":"2021-08-09","cited_by_count":85},{"id":"2107.03451","title":"Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling","created":"2021-07-07","cited_by_count":78},{"id":"2304.12298","title":"BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT","created":"2023-02-21","cited_by_count":76},{"id":"2106.11410","title":"A Survey of Race, Racism, and Anti-Racism in NLP","created":"2021-06-21","cited_by_count":75},{"id":"2011.02839","title":"Chasing Carbon: The Elusive Environmental Footprint of Computing","created":"2020-10-28","cited_by_count":72},{"id":"2010.15581","title":"The De-democratization of AI: Deep Learning and the Compute Divide in Artificial Intelligence Research","created":"2020-10-22","cited_by_count":67},{"id":"2006.08328","title":"ETHOS: an Online Hate Speech Detection Dataset","created":"2020-06-11","cited_by_count":66},{"id":"1912.08320","title":"Garbage In, Garbage Out? Do Machine Learning Application Papers in Social Computing Report Where Human-Labeled Training Data Comes From?","created":"2019-12-17","cited_by_count":64},{"id":"2302.04844","title":"The Gradient of Generative AI Release: Methods and Considerations","created":"2023-02-05","cited_by_count":63},{"id":"2106.11872","title":"Randomness In Neural Network Training: Characterizing The Impact of Tooling","created":"2021-06-22","cited_by_count":59},{"id":"2205.04610","title":"Towards Intersectionality in Machine Learning: Including More Identities, Handling Underrepresentation, and Performing Evaluation","created":"2022-05-10","cited_by_count":59},{"id":"2206.08931","title":"CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation","created":"2022-06-09","cited_by_count":59},{"id":"2011.02282","title":"\"What We Can't Measure, We Can't Understand\": Challenges to Demographic Data Procurement in the Pursuit of Fairness","created":"2020-10-30","cited_by_count":56},{"id":"2305.09941","title":"\"I'm fully who I am\": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation","created":"2023-05-17","cited_by_count":56},{"id":"2205.05256","title":"Evaluation Gaps in Machine Learning Practice","created":"2022-05-11","cited_by_count":49},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49},{"id":"2110.03036","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","created":"2021-10-06","cited_by_count":47},{"id":"2304.12397","title":"On the Challenges of Using Black-Box APIs for Toxicity Evaluation in Research","created":"2023-04-24","cited_by_count":44},{"id":"2006.03541","title":"Sentiment Analysis Based on Deep Learning: A Comparative Study","created":"2020-06-05","cited_by_count":37},{"id":"2101.11974","title":"Disembodied Machine Learning: On the Illusion of Objectivity in NLP","created":"2021-01-28","cited_by_count":37},{"id":"2206.03216","title":"Data Governance in the Age of Large-Scale Data-Driven Language Technology","created":"2022-05-04","cited_by_count":33},{"id":"2302.14035","title":"The ROOTS Search Tool: Data Transparency for LLMs","created":"2023-02-27","cited_by_count":31},{"id":"2205.04221","title":"The Forgotten Margins of AI Ethics","created":"2022-05-09","cited_by_count":30},{"id":"2305.09800","title":"Mirages: On Anthropomorphism in Dialogue Systems","created":"2023-05-16","cited_by_count":30},{"id":"2110.07871","title":"Socially Aware Bias Measurements for Hindi Language Representations","created":"2021-10-15","cited_by_count":29},{"id":"2305.01776","title":"Taxonomizing and Measuring Representational Harms: A Look at Image Tagging","created":"2023-05-02","cited_by_count":25},{"id":"2207.14157","title":"A Hazard Analysis Framework for Code Synthesis Large Language Models","created":"2022-07-25","cited_by_count":22},{"id":"2211.02738","title":"Intriguing Properties of Compression on Multilingual Models","created":"2022-11-04","cited_by_count":15},{"id":"2303.00586","title":"FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling","created":"2023-03-01","cited_by_count":11},{"id":"1804.10999","title":"But Who Protects the Moderators? The Case of Crowdsourced Image Moderation","created":"2018-04-29","cited_by_count":9},{"id":"2305.12757","title":"This Prompt is Measuring <MASK>: Evaluating Bias Evaluation in Language Models","created":"2023-05-22","cited_by_count":9},{"id":"2202.00885","title":"Opted Out, Yet Tracked: Are Regulations Enough to Protect Your Privacy?","created":"2022-02-02","cited_by_count":4},{"id":"2210.06245","title":"Back to the Future: On Potential Histories in NLP","created":"2022-10-12","cited_by_count":3},{"id":"2202.02647","title":"Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models","created":"2022-02-05","cited_by_count":1}],"next_cursor":null}