{"total":29,"rows":[{"id":"2308.13387","title":"Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs","created":"2023-08-25","cited_by_count":184,"area":null},{"id":"2205.00501","title":"Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation","created":"2022-05-01","cited_by_count":69,"area":null},{"id":"2305.06969","title":"A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges","created":"2023-05-11","cited_by_count":41,"area":null},{"id":"2210.14975","title":"MABEL: Attenuating Gender Bias using Textual Entailment Data","created":"2022-10-26","cited_by_count":31,"area":null},{"id":"2306.08158","title":"Sociodemographic Bias in Language Models: A Survey and Forward Path","created":"2023-06-13","cited_by_count":28,"area":null},{"id":"2205.02393","title":"Optimising Equal Opportunity Fairness in Model Training","created":"2022-05-05","cited_by_count":22,"area":null},{"id":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22,"area":null},{"id":"2210.07455","title":"Controlling Bias Exposure for Fair Interpretable Predictions","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2302.12578","title":"Fairness in Language Models Beyond English: Gaps and Challenges","created":"2023-02-24","cited_by_count":16,"area":null},{"id":"2202.00035","title":"Learning Fair Representations via Rate-Distortion Maximization","created":"2022-01-31","cited_by_count":15,"area":null},{"id":"2302.05711","title":"Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP","created":"2023-02-11","cited_by_count":11,"area":null},{"id":"2407.18454","title":"Fairness Definitions in Language Models Explained","created":"2024-07-26","cited_by_count":11,"area":null},{"id":"2305.06074","title":"iLab at SemEval-2023 Task 11 Le-Wi-Di: Modelling Disagreement or Modelling Perspectives?","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2203.06317","title":"Towards Equal Opportunity Fairness through Adversarial Learning","created":"2022-03-12","cited_by_count":8,"area":null},{"id":"2502.10407","title":"Addressing Bias in Generative AI: Challenges and Research Opportunities in Information Management","created":"2025-01-22","cited_by_count":7,"area":null},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2312.14626","title":"DSAP: Analyzing Bias Through Demographic Comparison of Datasets","created":"2023-12-22","cited_by_count":5,"area":null},{"id":"2404.00463","title":"Addressing Both Statistical and Causal Gender Fairness in NLP Models","created":"2024-03-30","cited_by_count":4,"area":null},{"id":"2210.08758","title":"Systematic Evaluation of Predictive Fairness","created":"2022-10-17","cited_by_count":3,"area":null},{"id":"2403.14727","title":"Protected group bias and stereotypes in Large Language Models","created":"2024-03-21","cited_by_count":3,"area":null},{"id":"2412.08167","title":"Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning Software","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2301.12139","title":"Bipol: Multi-axes Evaluation of Bias with Explainability in Benchmark Datasets","created":"2023-01-28","cited_by_count":2,"area":null},{"id":"2305.12495","title":"Fair Without Leveling Down: A New Intersectional Fairness Definition","created":"2023-05-21","cited_by_count":1,"area":null},{"id":"2402.11710","title":"A Note on Bias to Complete","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2305.12671","title":"Transferring Fairness using Multi-Task Learning with Limited Demographic Information","created":"2023-05-22","cited_by_count":0,"area":null},{"id":"2306.13064","title":"Auditing Predictive Models for Intersectional Biases","created":"2023-06-22","cited_by_count":0,"area":null},{"id":"2407.19345","title":"Inference-Time Selective Debiasing to Enhance Fairness in Text Classification Models","created":"2024-07-27","cited_by_count":0,"area":null},{"id":"2505.17642","title":"A Survey on Stereotype Detection in Natural Language Processing","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2508.16752","title":"A Framework for Benchmarking Fairness-Utility Trade-offs in Text-to-Image Models via Pareto Frontiers","created":"2025-08-22","cited_by_count":0,"area":null}],"next_cursor":null}