The rapid advancement of Vision-Language models (VLMs) has raised growing concerns that their black-box reasoning processes could lead to unintended forms of social bias. Current debiasing approaches focus on mitigating surface-level bias signals through post-hoc learning or test-time algorithms, while leaving the internal dynamics of the model largely unexplored. In this work, we introduce an interpretable, model-agnostic bias mitigation framework, DeBiasLens, that localizes social attribute neurons in VLMs through sparse autoencoders (SAEs) applied to multimodal encoders. Building upon the disentanglement ability of SAEs, we train them on facial image or caption datasets without corresponding social attribute labels to uncover neurons highly responsive to specific demographics, including those that are underrepresented. By selectively deactivating the social neurons most strongly tied to bias for each group, we effectively mitigate socially biased behaviors of VLMs without degrading their semantic knowledge. Our research lays the groundwork for future auditing tools, prioritizing social fairness in emerging real-world AI systems.
Large pre-trained vision-language models (VLMs) reduce the time for developing predictive models for various vision-grounded language downstream tasks by providing rich, adaptable image and text representations. However, these models suffer from societal biases owing to the skewed distribution of various identity groups in the training data. These biases manifest as the skewed similarity between the representations for specific text concepts and images of people of different identity groups and, therefore, limit the usefulness of such models in real-world high-stakes applications. In this work…
Latent space bias directions in LLMs capture confidence, not fairness
Institute of Astronomy & Kavli Institute for Cosmology, University of Cambridge（剑桥大学天文学研究所及卡夫利宇宙学研究所）；Risk and Security AI Lab, Visa Inc.（Visa公司风险与安全人工智能实验室）
Prompting Fairness: Integrating Causality to Debias Large Language Models
Google DeepMind（谷歌DeepMind）；Carnegie Mellon University（卡内基梅隆大学）；University of Maryland, College Park（马里兰大学帕克分校）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of California, Santa Cruz（加州大学圣克鲁兹分校）
Identifying and Mitigating Social Bias Knowledge in Language Models
Zhejiang University（浙江大学）；Nanyang Technological University（南洋理工大学）；Angelalign Technology Inc.（时代天使科技有限公司）；A*STAR Centre for Frontier AI Research（新加坡科研局前沿人工智能研究中心）；ZJU-Angelalign R&D Center for Intelligence Healthcare（浙江大学时代天使智能医疗研发中心）
debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Harvard Medical School（哈佛医学院）；Mass General Brigham（麻省总医院布里格姆医疗系统）；Boston Children’s Hospital（波士顿儿童医院）
Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
School of Informatics, Xiamen University, China（厦门大学信息学院）；vivo AI Lab, China（vivo AI实验室）；Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan (Xiamen University), Ministry of Culture and Tourism, China（福建省和台湾非物质文化遗产数字化保护与智能处理重点实验室（厦门大学），文化部，中国）
LLM4Rec: Large Language Models for Multimodal Generative Recommendation with Causal Debiasing
Department of Software \& Microelectronics Peking University Beijing, China；Department of Software \& Microelectronics Peking University Beijing, China hangli\；Department of Software \& Microelectronics Peking University Beijing, China zehua\；Department of Software \& Microelectronics Peking University Beijing, China xiaofan\；Economic Law School China University of Political Science；Peking University Changsha, China
HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；School of Software Technology, Zhejiang University, Ningbo, China（浙江大学宁波校区软件学院）；Ningbo Global Innovation Center, Zhejiang University, Ningbo, China（浙江大学宁波全球创新中心）；Collaborative Innovation Center of Novel Software Technology and Industrialization（新型软件技术与产业化协同创新中心）
Machine learning fairness concerns about the biases towards certain protected or sensitive group of people when addressing the target tasks. This paper studies the debiasing problem in the context of image classification tasks. Our data analysis on facial attribute recognition demonstrates (1) the attribution of model bias from imbalanced training data distribution and (2) the potential of adversarial examples in balancing data distribution. We are thus motivated to employ adversarial example to augment the training data for visual debiasing. Specifically, to ensure the adversarial generalizat…
Fairness-Aware Grouping for Continuous Sensitive Variables: Application for Debiasing Face Analysis with respect to Skin Tone
Artefact Research Center, Paris, France（阿切夫特研究中心，法国巴黎）；Institut de Mathématiques de Toulouse (UMR 5219), CNRS, Université de Toulouse, F-31062 Toulouse, France（图卢兹数学研究所（UMR 5219），CNRS，图卢兹大学，法国图卢兹）；L’Oréal Research（欧莱雅研究）；INRIA, ANITI, France（INRIA，ANITI，法国）
Deep learning models often learn to make predictions that rely on sensitive social attributes like gender and race, which poses significant fairness risks, especially in societal applications, e.g., hiring, banking, and criminal justice. Existing work tackles this issue by minimizing information about social attributes in models for debiasing. However, the high correlation between target task and social attributes makes bias mitigation incompatible with target task accuracy. Recalling that model bias arises because the learning of features in regard to bias attributes (i.e., bias features) hel…
FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models
School of Computer Science and Engineering, University of New South Wales, Australia.（新南威尔士大学计算机科学与工程学院，澳大利亚）；State Key Laboratory for Novel Software Technology, Nanjing University, China（南京大学新型软件技术国家重点实验室，中国）
The Johns Hopkins University Applied Physics Laboratory（约翰斯·霍普金斯大学应用物理实验室）；Queens University（女王大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
We propose a novel method for enforcing AI fairness with respect to protected or sensitive factors. This method uses a dual strategy performing training and representation alteration (TARA) for the mitigation of prominent causes of AI bias by including: a) the use of representation learning alteration via adversarial independence to suppress the bias-inducing dependence of the data representation from protected factors; and b) training set alteration via intelligent augmentation to address bias-causing data imbalance, by using generative models that allow the fine control of sensitive factors …
As transformer architectures become increasingly prevalent in computer vision, it is critical to understand their fairness implications. We perform the first study of the fairness of transformers applied to computer vision and benchmark several bias mitigation approaches from prior work. We visualize the feature space of the transformer self-attention modules and discover that a significant portion of the bias is encoded in the query matrix. With this knowledge, we propose TADeT, a targeted alignment strategy for debiasing transformers that aims to discover and remove bias primarily from query…
