{"list":"other","total":53,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"1610.02413","title":"Equality of Opportunity in Supervised Learning","created":"2016-10-07","cited_by_count":2007},{"id":"2408.00118","title":"Gemma 2: Improving Open Language Models at a Practical Size","created":"2024-07-31","cited_by_count":1998},{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917},{"id":"2009.11462","title":"RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models","created":"2020-09-24","cited_by_count":1255},{"id":"2305.17926","title":"Large Language Models are not Fair Evaluators","created":"2023-05-29","cited_by_count":1085},{"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":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"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":"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":"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":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449},{"id":"2105.03023","title":"DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts","created":"2021-05-07","cited_by_count":441},{"id":"1709.02012","title":"On Fairness and Calibration","created":"2017-09-06","cited_by_count":406},{"id":"1701.08230","title":"Algorithmic decision making and the cost of fairness","created":"2017-01-28","cited_by_count":403},{"id":"2212.09689","title":"Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor","created":"2022-12-19","cited_by_count":397},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2402.10669","title":"Humans or LLMs as the Judge? A Study on Judgement Biases","created":"2024-02-16","cited_by_count":323},{"id":"2010.03240","title":"Bias and Debias in Recommender System: A Survey and Future Directions","created":"2020-10-07","cited_by_count":240},{"id":"1511.00830","title":"The Variational Fair Autoencoder","created":"2015-11-03","cited_by_count":223},{"id":"2105.04054","title":"Societal Biases in Language Generation: Progress and Challenges","created":"2021-05-10","cited_by_count":202},{"id":"1906.02589","title":"Flexibly Fair Representation Learning by Disentanglement","created":"2019-06-06","cited_by_count":196},{"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":"1805.11202","title":"FairGAN: Fairness-aware Generative Adversarial Networks","created":"2018-05-28","cited_by_count":164},{"id":"2205.09209","title":"\"I'm sorry to hear that\": Finding New Biases in Language Models with a Holistic Descriptor Dataset","created":"2022-05-18","cited_by_count":162},{"id":"2309.17012","title":"Benchmarking Cognitive Biases in Large Language Models as Evaluators","created":"2023-09-29","cited_by_count":150},{"id":"1806.06055","title":"Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees","created":"2018-06-15","cited_by_count":146},{"id":"1905.13662","title":"On the Fairness of Disentangled Representations","created":"2019-05-31","cited_by_count":144},{"id":"1611.02796","title":"Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control","created":"2016-11-09","cited_by_count":101},{"id":"2404.11457","title":"Bias and Unfairness in Information Retrieval Systems: New Challenges in the LLM Era","created":"2024-04-17","cited_by_count":98},{"id":"1812.02696","title":"Differentially Private Fair Learning","created":"2018-12-06","cited_by_count":76},{"id":"1601.05764","title":"A Confidence-Based Approach for Balancing Fairness and Accuracy","created":"2016-01-21","cited_by_count":73},{"id":"1906.05082","title":"Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification","created":"2019-06-12","cited_by_count":60},{"id":"1804.06500","title":"Two-Player Games for Efficient Non-Convex Constrained Optimization","created":"2018-04-17","cited_by_count":55},{"id":"1807.00028","title":"Training Well-Generalizing Classifiers for Fairness Metrics and Other Data-Dependent Constraints","created":"2018-06-29","cited_by_count":53},{"id":"2405.18634","title":"A Theoretical Understanding of Self-Correction through In-context Alignment","created":"2024-05-28","cited_by_count":44},{"id":"1610.08077","title":"A statistical framework for fair predictive algorithms","created":"2016-10-25","cited_by_count":38},{"id":"2001.11358","title":"Correcting for Selection Bias in Learning-to-rank Systems","created":"2020-01-29","cited_by_count":35},{"id":"2202.09724","title":"Bayes-Optimal Classifiers under Group Fairness","created":"2022-02-20","cited_by_count":24},{"id":"2109.07946","title":"Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation","created":"2021-09-16","cited_by_count":23},{"id":"2312.15398","title":"Fairness-Aware Structured Pruning in Transformers","created":"2023-12-24","cited_by_count":22},{"id":"2111.04271","title":"Group-Aware Threshold Adaptation for Fair Classification","created":"2021-11-08","cited_by_count":21},{"id":"2202.13446","title":"The Unfairness of Popularity Bias in Book Recommendation","created":"2022-02-27","cited_by_count":14},{"id":"2310.16738","title":"Improving Conversational Recommendation Systems via Bias Analysis and Language-Model-Enhanced Data Augmentation","created":"2023-10-25","cited_by_count":11}],"next_cursor":null}