{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"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":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2005.14050","title":"Language (Technology) is Power: A Critical Survey of \"Bias\" in NLP","created":"2020-05-28","cited_by_count":956},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"id":"2307.15217","title":"Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback","created":"2023-07-27","cited_by_count":759},{"id":"1412.3756","title":"Certifying and removing disparate impact","created":"2014-12-11","cited_by_count":715},{"id":"2110.08193","title":"BBQ: A Hand-Built Bias Benchmark for Question Answering","created":"2021-10-15","cited_by_count":701},{"id":"1610.07524","title":"Fair prediction with disparate impact: A study of bias in recidivism prediction instruments","created":"2016-10-24","cited_by_count":672},{"id":"1804.06876","title":"Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods","created":"2018-04-18","cited_by_count":659},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"1609.05807","title":"Inherent Trade-Offs in the Fair Determination of Risk Scores","created":"2016-09-19","cited_by_count":586},{"id":"2309.05463","title":"Textbooks Are All You Need II: phi-1.5 technical report","created":"2023-09-11","cited_by_count":565},{"id":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2101.11718","title":"BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation","created":"2021-01-27","cited_by_count":412},{"id":"1701.08230","title":"Algorithmic decision making and the cost of fairness","created":"2017-01-28","cited_by_count":403},{"id":"2305.03047","title":"Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision","created":"2023-05-04","cited_by_count":318},{"id":"1903.03862","title":"Lipstick on a Pig: Debiasing Methods Cover up Systematic Gender Biases in Word Embeddings But do not Remove Them","created":"2019-03-09","cited_by_count":268},{"id":"2006.13114","title":"Fairness without Demographics through Adversarially Reweighted Learning","created":"2020-06-23","cited_by_count":251},{"id":"1809.01496","title":"Learning Gender-Neutral Word Embeddings","created":"2018-08-29","cited_by_count":169},{"id":"1712.03586","title":"Fairness in Machine Learning: Lessons from Political Philosophy","created":"2017-12-10","cited_by_count":149},{"id":"2012.15859","title":"Intrinsic Bias Metrics Do Not Correlate with Application Bias","created":"2020-12-31","cited_by_count":148},{"id":"2209.07572","title":"Power to the People? Opportunities and Challenges for Participatory AI","created":"2022-09-15","cited_by_count":138},{"id":"2312.03689","title":"Evaluating and Mitigating Discrimination in Language Model Decisions","created":"2023-12-06","cited_by_count":124},{"id":"2305.07609","title":"Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation","created":"2023-05-12","cited_by_count":114},{"id":"1906.00285","title":"Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination","created":"2019-06-01","cited_by_count":79},{"id":"1707.00093","title":"Multisided Fairness for Recommendation","created":"2017-07-01","cited_by_count":70},{"id":"2112.05675","title":"Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Support","created":"2021-12-10","cited_by_count":63},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62},{"id":"2404.01349","title":"Fairness in Large Language Models: A Taxonomic Survey","created":"2024-03-31","cited_by_count":58},{"id":"2206.08325","title":"Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models","created":"2022-06-16","cited_by_count":49},{"id":"2104.14537","title":"Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features","created":"2021-04-29","cited_by_count":45},{"id":"1806.06122","title":"Fairness Under Composition","created":"2018-06-15","cited_by_count":43},{"id":"2402.12649","title":"Bias in Language Models: Beyond Trick Tests and Toward RUTEd Evaluation","created":"2024-02-20","cited_by_count":41},{"id":"2012.10713","title":"Fundamental Limits and Tradeoffs in Invariant Representation Learning","created":"2020-12-19","cited_by_count":38},{"id":"2307.03744","title":"Comparing Traditional and LLM-based Search for Consumer Choice: A Randomized Experiment","created":"2023-07-07","cited_by_count":36},{"id":"2309.15337","title":"Beyond the Chat: Executable and Verifiable Text-Editing with LLMs","created":"2023-09-27","cited_by_count":35},{"id":"2402.07282","title":"How do Large Language Models Navigate Conflicts between Honesty and Helpfulness?","created":"2024-02-11","cited_by_count":27},{"id":"2010.01470","title":"User Fairness, Item Fairness, and Diversity for Rankings in Two-Sided Markets","created":"2020-10-04","cited_by_count":23},{"id":"2401.06408","title":"AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters","created":"2024-01-12","cited_by_count":22},{"id":"2310.19691","title":"Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness","created":"2023-10-30","cited_by_count":17},{"id":"1705.10689","title":"Auditing Search Engines for Differential Satisfaction Across Demographics","created":"2017-05-24","cited_by_count":12},{"id":"1809.03577","title":"Using Image Fairness Representations in Diversity-Based Re-ranking for Recommendations","created":"2018-09-10","cited_by_count":11},{"id":"2107.03483","title":"Impossibility results for fair representations","created":"2021-07-07","cited_by_count":10},{"id":"2210.02516","title":"Equalizing Credit Opportunity in Algorithms: Aligning Algorithmic Fairness Research with U.S. Fair Lending Regulation","created":"2022-10-05","cited_by_count":9},{"id":"2304.11217","title":"ACROCPoLis: A Descriptive Framework for Making Sense of Fairness","created":"2023-04-19","cited_by_count":8},{"id":"2206.13747","title":"Fire Dragon and Unicorn Princess; Gender Stereotypes and Children's Products in Search Engine Responses","created":"2022-06-28","cited_by_count":2},{"id":"2103.05114","title":"Learning Invariant Representations across Domains and Tasks","created":"2021-03-03","cited_by_count":1},{"id":"2209.02662","title":"Matching Consumer Fairness Objectives & Strategies for RecSys","created":"2022-09-06","cited_by_count":1}],"next_cursor":null}