Fairness

Thinking Racial Bias in Fair Forgery Detection: Models, Datasets and Evaluations AAAI 2025 Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate Speech. ACL 2025 TitleTrap: Probing Presentation Bias in LLM-Based Scientific Reviewing AACL 2025 TLDR: Text Based Last-Layer Retraining for Debiasing Image Classifiers WACV 2025 Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks EMNLP 2025 Toward Fair and Accurate Cross-Domain Medical Image Segmentation: A VLM-Driven Active Domain Adaptation Paradigm ICCV 2025 Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable Mitigation of Social Biases in LLMs EMNLP 2025 Towards Author-informed NLP: Mind the Social Bias EMNLP 2025 Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and Enhancement ACL 2025 Towards counterfactual fairness through auxiliary variables ICLR 2025 Towards Explainable Hate Speech Detection ACL 2025 Towards Fairness Assessment of Dutch Hate Speech Detection ACL 2025 Towards Fairness with Limited Demographics via Disentangled Learning IJCAI 2025 Towards Macro-AUC Oriented Imbalanced Multi-Label Continual Learning AAAI 2025 Towards Massive Multilingual Holistic Bias ACL 2025 Towards Region-aware Bias Evaluation Metrics NAACL 2025 Towards Reward Fairness in RLHF: From a Resource Allocation Perspective ACL 2025 Towards Robust ESG Analysis Against Greenwashing Risks: Aspect-Action Analysis with Cross-Category Generalization ACL 2025 Towards Safer Pretraining: Analyzing and Filtering Harmful Content in Webscale Datasets for Responsible LLMs IJCAI 2025 Towards Scalable Human-aligned Benchmark for Text-guided Image Editing CVPR 2025 Towards Unbiased Continual Learning: Avoiding Forgetting in the Presence of Spurious Correlations WACV 2025 Towards Universal Debiasing for Language Models-based Tabular Data Generation EMNLP 2025 Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore’s Low-Resource Languages EMNLP 2025 Training-free LLM-generated Text Detection by Mining Token Probability Sequences ICLR 2025 Training Robust Ensembles Requires Rethinking Lipschitz Continuity ICLR 2025