Fairness

A Trip Towards Fairness: Bias and De-Biasing in Large Language Models NAACL 2024 Auditing Fairness under Unobserved Confounding AISTATS 2024 Auditing Local Explanations is Hard NeurIPS 2024 Auditing Privacy Mechanisms via Label Inference Attacks NeurIPS 2024 A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks NeurIPS 2024 A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models EMNLP 2024 A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems NeurIPS 2024 Automatic Children Speech Sound Disorder Detection with Age and Speaker Bias Mitigation Interspeech 2024 Automatic Generation of Model and Data Cards: A Step Towards Responsible AI NAACL 2024 Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions NeurIPS 2024 Backdoor Adjustment via Group Adaptation for Debiased Coupon Recommendations AAAI 2024 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 BadFair: Backdoored Fairness Attacks with Group-conditioned Triggers EMNLP 2024 Balancing Act: Constraining Disparate Impact in Sparse Models ICLR 2024 Balancing Act: Distribution-Guided Debiasing in Diffusion Models CVPR 2024 BAN-PL: A Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl Web Service COLING 2024 B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable NeurIPS 2024 BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text NeurIPS 2024 BELIEVE: Belief-Enhanced Instruction Generation and Augmentation for Zero-Shot Bias Mitigation NAACL 2024 Benchmark Data Repositories for Better Benchmarking NeurIPS 2024 BendVLM: Test-Time Debiasing of Vision-Language Embeddings NeurIPS 2024 BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices NeurIPS 2024 Beyond Aesthetics: Cultural Competence in Text-to-Image Models NeurIPS 2024 Beyond Binary Gender Labels: Revealing Gender Bias in LLMs through Gender-Neutral Name Predictions ACL 2024 Beyond Binary: Towards Embracing Complexities in Cyberbullying Detection and Intervention - a Position Paper COLING 2024