{"list":"other","total":68,"rows":[{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2109.07958","title":"TruthfulQA: Measuring How Models Mimic Human Falsehoods","created":"2021-09-08","cited_by_count":2975},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095},{"id":"2112.00861","title":"A General Language Assistant as a Laboratory for Alignment","created":"2021-12-01","cited_by_count":1055},{"id":"2009.09025","title":"COMET: A Neural Framework for MT Evaluation","created":"2020-09-18","cited_by_count":1033},{"id":"2303.17548","title":"Whose Opinions Do Language Models Reflect?","created":"2023-03-30","cited_by_count":773},{"id":"1703.04009","title":"Automated Hate Speech Detection and the Problem of Offensive Language","created":"2017-03-11","cited_by_count":736},{"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":"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":"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":"2001.09768","title":"Artificial Intelligence, Values and Alignment","created":"2020-01-13","cited_by_count":448},{"id":"2306.16388","title":"Towards Measuring the Representation of Subjective Global Opinions in Language Models","created":"2023-06-28","cited_by_count":437},{"id":"1711.05144","title":"Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness","created":"2017-11-14","cited_by_count":384},{"id":"1806.08010","title":"Fairness Without Demographics in Repeated Loss Minimization","created":"2018-06-20","cited_by_count":364},{"id":"2111.15366","title":"AI and the Everything in the Whole Wide World Benchmark","created":"2021-11-26","cited_by_count":349},{"id":"2110.01963","title":"Multimodal datasets: misogyny, pornography, and malignant stereotypes","created":"2021-10-05","cited_by_count":327},{"id":"2110.05719","title":"Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations","created":"2021-10-12","cited_by_count":314},{"id":"1912.05511","title":"Measurement and Fairness","created":"2019-12-11","cited_by_count":308},{"id":"2212.09720","title":"The case for 4-bit precision: k-bit Inference Scaling Laws","created":"2022-12-19","cited_by_count":251},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2005.09093","title":"Are All Languages Created Equal in Multilingual BERT?","created":"2020-05-18","cited_by_count":207},{"id":"1901.10002","title":"A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle","created":"2019-01-28","cited_by_count":193},{"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":"2106.15590","title":"The Values Encoded in Machine Learning Research","created":"2021-06-29","cited_by_count":172},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"1906.02659","title":"Does Object Recognition Work for Everyone?","created":"2019-06-06","cited_by_count":151},{"id":"2108.12084","title":"Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies","created":"2021-08-27","cited_by_count":128},{"id":"2202.02950","title":"Jury Learning: Integrating Dissenting Voices into Machine Learning Models","created":"2022-02-07","cited_by_count":118},{"id":"2007.02423","title":"Participation is not a Design Fix for Machine Learning","created":"2020-07-05","cited_by_count":111},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109},{"id":"2101.09995","title":"Re-imagining Algorithmic Fairness in India and Beyond","created":"2021-01-25","cited_by_count":104},{"id":"2006.07264","title":"Low-resource Languages: A Review of Past Work and Future Challenges","created":"2020-06-12","cited_by_count":91},{"id":"2306.11247","title":"DICES Dataset: Diversity in Conversational AI Evaluation for Safety","created":"2023-06-20","cited_by_count":86},{"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":"2211.02011","title":"Inverse scaling can become U-shaped","created":"2022-11-03","cited_by_count":76},{"id":"1803.01937","title":"ROUGE 2.0: Updated and Improved Measures for Evaluation of Summarization Tasks","created":"2018-03-05","cited_by_count":67},{"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":"2206.08931","title":"CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation","created":"2022-06-09","cited_by_count":59},{"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":"2112.04554","title":"Whose Ground Truth? Accounting for Individual and Collective Identities Underlying Dataset Annotation","created":"2021-12-08","cited_by_count":52},{"id":"2205.07722","title":"How Different Groups Prioritize Ethical Values for Responsible AI","created":"2022-05-16","cited_by_count":49},{"id":"2103.06076","title":"Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs","created":"2021-03-10","cited_by_count":48},{"id":"1905.01395","title":"On the Difficulty of Evaluating Baselines: A Study on Recommender Systems","created":"2019-05-04","cited_by_count":46},{"id":"2101.01673","title":"Characterizing Intersectional Group Fairness with Worst-Case Comparisons","created":"2021-01-05","cited_by_count":42},{"id":"2301.13442","title":"Scaling laws for single-agent reinforcement learning","created":"2023-01-31","cited_by_count":41},{"id":"2002.08512","title":"The Problem with Metrics is a Fundamental Problem for AI","created":"2020-02-20","cited_by_count":37},{"id":"2303.16972","title":"Queer In AI: A Case Study in Community-Led Participatory AI","created":"2023-03-29","cited_by_count":34},{"id":"2306.13141","title":"On Hate Scaling Laws For Data-Swamps","created":"2023-06-22","cited_by_count":28},{"id":"2111.01122","title":"Stakeholder Participation in AI: Beyond \"Add Diverse Stakeholders and Stir\"","created":"2021-11-01","cited_by_count":26},{"id":"2303.17555","title":"Factoring the Matrix of Domination: A Critical Review and Reimagination of Intersectionality in AI Fairness","created":"2023-03-16","cited_by_count":26},{"id":"2305.09022","title":"It Takes Two to Tango: Navigating Conceptualizations of NLP Tasks and Measurements of Performance","created":"2023-05-15","cited_by_count":26},{"id":"2202.06387","title":"Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments","created":"2022-02-13","cited_by_count":23},{"id":"2202.09519","title":"The four-fifths rule is not disparate impact: a woeful tale of epistemic trespassing in algorithmic fairness","created":"2022-02-19","cited_by_count":21},{"id":"2010.08850","title":"Against Scale: Provocations and Resistances to Scale Thinking","created":"2020-10-17","cited_by_count":18},{"id":"2101.03827","title":"Representativeness in Statistics, Politics, and Machine Learning","created":"2021-01-11","cited_by_count":17},{"id":"1403.7400","title":"Big Questions for Social Media Big Data: Representativeness, Validity and Other Methodological Pitfalls","created":"2014-03-28","cited_by_count":12},{"id":"2106.01784","title":"The Contestation of Tech Ethics: A Sociotechnical Approach to Technology Ethics in Practice","created":"2021-06-03","cited_by_count":12},{"id":"2301.09406","title":"The Reasonable Effectiveness of Diverse Evaluation Data","created":"2023-01-23","cited_by_count":10},{"id":"2107.08096","title":"Learning to Limit Data Collection via Scaling Laws: A Computational Interpretation for the Legal Principle of Data Minimization","created":"2021-07-16","cited_by_count":9},{"id":"2206.11484","title":"Towards WinoQueer: Developing a Benchmark for Anti-Queer Bias in Large Language Models","created":"2022-06-23","cited_by_count":8},{"id":"2211.06348","title":"Striving for data-model efficiency: Identifying data externalities on group performance","created":"2022-11-11","cited_by_count":4},{"id":"2211.11206","title":"Cultural Re-contextualization of Fairness Research in Language Technologies in India","created":"2022-11-21","cited_by_count":4}],"next_cursor":null}