Text-to-Image diffusion models often propagate harmful bias inherited from the training data. Existing bias mitigation techniques typically intervene only at the text encoder or provide inference-time guidance, often leading to generations that collapse into semantically incoherent outputs. To address these limitations, we introduce CO-ALIGN (Concept Ontology Alignment), a novel bias mitigation approach based on concept-graph alignment that operates on the model's internal concept ontology. By aligning concepts within the text encoder and denoiser, CO-ALIGN achieves substantial bias reduction while preserving generative integrity. We demonstrate the effectiveness of concept-graph alignment across three paradigms: text-encoders, denoisers and joint text-denoiser ontology alignment. CO-ALIGN outperforms the state of the art, improving fairness by $30\%$, $ΔFID=11.4$ in image quality, $2.8\%$ in image fidelity, all while reducing semantically incoherent outputs by $88\%$. Beyond bias mitigation, we show that CO-ALIGN benefits other downstream tasks as well. In particular, our experiments demonstrate that better-aligned internal ontologies enhance concept unlearning robustness across multiple unlearning techniques.
BiasMap: Leveraging Cross-Attentions to Discover and Mitigate Hidden Social Biases in Text-to-Image Generation
Institute for Clarity in Documentation（清晰文档研究所）；Inria Paris-Rocquencourt（巴黎-罗克琴court研究所）；Rajiv Gandhi University（拉吉夫·甘地大学）；Tsinghua University（清华大学）；Palmer Research Laboratories（帕勒尔研究实验室）；University of North Carolina at Charlotte（北卡罗来纳大学教堂山分校）；Utah State University（犹他州立大学）
Operationalizing Fairness in Text-to-Image Models: A Survey of Bias, Fairness Audits and Mitigation Strategies
AImotion Bavaria, Technische Hochschule Ingolstadt（AImotion巴伐利亚、因戈尔施塔特技术大学）；School of Transformation and Sustainability, Catholic University of Eichstätt-Ingolstadt（转型与可持续性学院，埃施塔特-因戈尔施塔特天主教大学）；Chair of Economic and Social Ethics, University of Hohenheim（经济与社会伦理系，霍亨海姆大学）
Understanding-informed Bias Mitigation for Fair CMR Segmentation
College of Electronic and Information Engineering, Tongji University（同济大学电子与信息工程学院）；Guy’s and St Thomas’ NHS Foundation Trust（盖茨和圣托马斯国家健康服务基金会信托）；HeartFlow Inc, United States（美国HeartFlow公司）；British Heart Foundation Centre, Department of Clinical Pharmacology, King’s College London（英国心脏基金会中心、伦敦国王学院临床药理学系）；School of Biomedical Engineering & Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与成像科学学院）
CORGI-PM: A Chinese Corpus For Gender Bias Probing and Mitigation
Beijing Academy of Artificial Intelligence（北京人工智能研究院）；The University of Sheffield（谢菲尔德大学）；University of Michigan（密歇根大学）；University of Colorado Boulder（科罗拉多大学博尔德分校）；Sichuan University（四川大学）；McGill University（麦吉尔大学）
Ensuring Medical AI Safety: Interpretability-Driven Detection and Mitigation of Spurious Model Behavior and Associated Data
Fraunhofer Heinrich Hertz Institut（弗劳恩霍夫 Heinrich Hertz 研究所）；Technische Universität Berlin（柏林技术大学）；Berlin Institute for the Foundations of Learning and Data (BIFOLD)（柏林学习与数据基础研究所（BIFOLD））
BiMa: Towards Biases Mitigation for Text-Video Retrieval via Scene Element Guidance
FPT Software AI Center（FPT软件AI中心）；Aalborg University（奥尔堡大学）；Pioneer Centre for AI（先锋人工智能中心）；University of Liverpool（利物浦大学）；AICV Lab, University of Arkansas（AICV实验室，阿肯色大学）
Parameter-efficient Modularised Bias Mitigation via AdapterFusion
Johannes Kepler University Linz（林茨约翰内斯·开普勒大学）；Brown University（布朗大学）；Dataminr（Dataminr公司）；University of Tübingen（图宾根大学）；Linz Institute of Technology（林茨技术研究所）
Simulating a Bias Mitigation Scenario in Large Language Models
Department of Computer Science, Bowling Green State University（计算机科学系，布恩维尔州立大学）；School of Computing, University of Nebraska–Lincoln（计算学院，内布拉斯加-林肯大学）；Department of Civil, Environmental, and Ocean Engineering, Stevens Institute of Technology（土木、环境与海洋工程系，史蒂文斯理工学院）；Department of Computer Science, University of South Carolina（计算机科学系，南卡罗来纳大学）；Artificial Intelligence Institute, University of South Carolina（人工智能研究院，南卡罗来纳大学）
Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers
Institute of Data Science, Faculty of Science and Engineering, Maastricht University（马斯特里赫特大学科学与工程学院数据科学研究所）；Department of Advanced Computing Sciences, Faculty of Science and Engineering, Maastricht University（马斯特里赫特大学科学与工程学院高级计算科学系）；VITO（比利时弗拉芒技术研究所）
Multi-Persona Thinking for Bias Mitigation in Large Language Models
Dept. Computing Science, Alberta Machine Intelligence Institute (Amii) University of Alberta, Canada（计算科学系，阿尔伯塔机器智能研究所（Amii），阿尔伯塔大学，加拿大）；Canada CIFAR AI Chair, Amii（加拿大 CIFAR 人工智能主席，Amii）
Tracing Partisan Bias to Its Emotional Fingerprints: A Computational Approach to Mitigation
aDepartment of Political Science, Trinity College Dublin, Dublin, Ireland；bGuangdong Provincial Key Laboratory of Interdisciplinary Research；cDepartment of Statistics；Data Science, Beijing Normal Hong Kong Baptist University., Zhuhai, China；dFaculty of Science, Hong Kong Baptist University, Hong Kong SAR, China；eHong Kong aiKnow Limited, Hong Kong SAR, China
本文提出基于 VAD 的情感指纹框架分析 Allsides 中不同党派媒体的语言偏见，并通过 NeutraSum 中和情感模式，生成更中性、偏见分数更低的摘要。
Wisdom from Diversity: Bias Mitigation Through Hybrid Human-LLM Crowds
Machine Learning Group, Université Libre de Bruxelles（布鲁塞尔自由大学机器学习组）；AI Lab, Vrije Universiteit Brussel（布鲁塞尔自由大学人工智能实验室）；FARI, AI for the Common-Good Institute, ULB-VUB（ULB-VUB共同利益人工智能研究所）；Center for Human-Compatible AI, UC Berkeley（伯克利人类兼容人工智能中心）
