Synthetic data generation creates data based on real-world data using generative models. In health applications, generating high-quality data while maintaining fairness for sensitive attributes is essential for equitable outcomes. Existing GAN-based and LLM-based methods focus on counterfactual fairness and are primarily applied in finance and legal domains. Causal fairness provides a more comprehensive evaluation framework by preserving causal structure, but current synthetic data generation methods do not address it in health settings. To fill this gap, we develop the first LLM-augmented synthetic data generation method to enhance causal fairness using real-world tabular health data. Our generated data deviates by less than 10% from real data on causal fairness metrics. When trained on causally fair predictors, synthetic data reduces bias on the sensitive attribute by 70% compared to real data. This work improves access to fair synthetic data, supporting equitable health research and healthcare delivery.
University of Cambridge（剑桥大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；The Alan Turing Institute（艾伦图灵研究所）
Machine learning models have been criticized for reflecting unfair biases in the training data. Instead of solving for this by introducing fair learning algorithms directly, we focus on generating fair synthetic data, such that any downstream learner is fair. Generating fair synthetic data from unfair data - while remaining truthful to the underlying data-generating process (DGP) - is non-trivial. In this paper, we introduce DECAF: a GAN-based fair synthetic data generator for tabular data. With DECAF we embed the DGP explicitly as a structural causal model in the input layers of the generator…
The Other Side of the Coin: Exploring Fairness in Retrieval-Augmented Generation
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学）；Nanyang Technological University（南洋理工大学）
PopResume: Causal Fairness Evaluation of LLM/VLM Resume Screeners with Population-Representative Dataset
ECE, Seoul National University（首尔国立大学电子与计算机工程系）；IPAI, Seoul National University（首尔国立大学人工智能研究所）；ASRI / INMC / AIIS, Seoul National University（首尔国立大学人工智能研究所）
Stanford Center for Biomedical Informatics Research（斯坦福生物医学信息学研究中心）；Stanford University（斯坦福大学）
The use of machine learning systems to support decision making in healthcare raises questions as to what extent these systems may introduce or exacerbate disparities in care for historically underrepresented and mistreated groups, due to biases implicitly embedded in observational data in electronic health records. To address this problem in the context of clinical risk prediction models, we develop an augmented counterfactual fairness criteria to extend the group fairness criteria of equalized odds to an individual level. We do so by requiring that the same prediction be made for a patient, a…
Debate about fairness in machine learning has largely centered around competing definitions of what fairness or nondiscrimination between groups requires. However, little attention has been paid to what precisely a group is. Many recent approaches to "fairness" require one to specify a causal model of the data generating process. These exercises make an implicit ontological assumption that a racial or sex group is simply a collection of individuals who share a given trait. We show this by exploring the formal assumption of modularity in causal models, which holds that the dependencies captured…
TrueGradeAI: Retrieval-Augmented and Bias-Resistant AI for Transparent and Explainable Digital Assessments
Amity Center for Artificial Intelligence, Amity University（阿米蒂大学人工智能中心，阿米蒂大学）；Amity School of Engineering and Technology, Amity University（阿米蒂工程科技学院，阿米蒂大学）
FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation
Sharif University of Technology（谢里夫理工大学）；Iran University of Science and Technology（伊朗科学技术大学）；Noor Avaran Jelvehaye Maanaei Najm Co., Ltd.（诺尔·阿瓦兰·杰拉维耶·马纳埃尼纳姆公司）
University of Virginia（弗吉尼亚大学）；City University of Hong Kong（香港城市大学）；Microsoft（微软）
Fair machine learning aims to mitigate the biases of model predictions against certain subpopulations regarding sensitive attributes such as race and gender. Among the many existing fairness notions, counterfactual fairness measures the model fairness from a causal perspective by comparing the predictions of each individual from the original data and the counterfactuals. In counterfactuals, the sensitive attribute values of this individual had been modified. Recently, a few works extend counterfactual fairness to graph data, but most of them neglect the following facts that can lead to biases:…
Jilin University（吉林大学）；RMIT University（皇家墨尔本理工大学）；Nanyang Technological University（南洋理工大学）；Dalian University of Technology（大连理工大学）；University of South Australia（澳大利亚南澳大利亚大学）；Hong Kong University of Science and Technology（香港科学与技术大学）
Università della Svizzera Italiana（瑞士意大利大学）；University of Liechtenstein（利赫泰森大学）；Politecnico di Torino（托尼诺理工学院）；IBM Research（IBM研究院）；Scuola Universitaria Professionale della Svizzera Italiana（瑞士意大利专业大学）
Position: LLMs Must Use Functor-Based and RAG-Driven Bias Mitigation for Fairness
Knight Foundation School of Computing and Information Sciences（骑士基金会计算与信息科学学院）；Florida International University（佛罗里达国际大学）；College of Engineering（工程学院）；University of South Florida（佛罗里达州立大学）
University of Iowa（爱荷华大学）；University of Texas at Austin（得克萨斯大学奥斯汀分校）
We propose a model-agnostic approach for mitigating the prediction bias of a black-box decision-maker, and in particular, a human decision-maker. Our method detects in the feature space where the black-box decision-maker is biased and replaces it with a few short decision rules, acting as a "fair surrogate". The rule-based surrogate model is trained under two objectives, predictive performance and fairness. Our model focuses on a setting that is common in practice but distinct from other literature on fairness. We only have black-box access to the model, and only a limited set of true labels c…
Institut de Mathématiques de Toulouse（图卢兹数学研究所）；University of the Basque Country（巴斯克大学）；IKERBASQUE（巴斯克科学基金会）；Institut Polytechnique de Paris（巴黎综合理工学院）；INRIA, Projet Regalia（法国国家信息与自动化研究所，Regalia项目）
Trustworthiness in Retrieval-Augmented Generation Systems: A Survey
Tsinghua University（清华大学）；Renmin University of China（中国人民大学）；The Chinese University of Hong Kong（香港中文大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Hong Kong Polytechnic University（香港理工大学）；Microsoft Research Asia（微软亚洲研究院）；University of Illinois（伊利诺伊大学）
University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；University of Illinois at Chicago（伊利诺伊大学芝加哥分校）
Algorithmic decision making based on computer vision and machine learning technologies continue to permeate our lives. But issues related to biases of these models and the extent to which they treat certain segments of the population unfairly, have led to concern in the general public. It is now accepted that because of biases in the datasets we present to the models, a fairness-oblivious training will lead to unfair models. An interesting topic is the study of mechanisms via which the de novo design or training of the model can be informed by fairness measures. Here, we study mechanisms that …
Indian Institute of Technology Hyderabad（印度理工学院海得拉巴分校）
Representation learners that disentangle factors of variation have already proven to be important in addressing various real world concerns such as fairness and interpretability. Initially consisting of unsupervised models with independence assumptions, more recently, weak supervision and correlated features have been explored, but without a causal view of the generative process. In contrast, we work under the regime of a causal generative process where generative factors are either independent or can be potentially confounded by a set of observed or unobserved confounders. We present an analy…
This thesis scrutinizes common assumptions underlying traditional machine learning approaches to fairness in consequential decision making. After challenging the validity of these assumptions in real-world applications, we propose ways to move forward when they are violated. First, we show that group fairness criteria purely based on statistical properties of observed data are fundamentally limited. Revisiting this limitation from a causal viewpoint we develop a more versatile conceptual framework, causal fairness criteria, and first algorithms to achieve them. We also provide tools to analyze…
Fair Graph Neural Network with Supervised Contrastive Regularization
Institut de Mathématiques de Toulouse（图卢兹数学研究所）；Université Toulouse 3（图卢兹第三大学）；University of the Basque Country UPV/EHU（巴斯克大学（UPV/EHU））；IKERBASQUE, Basque Foundation for Science（伊克尔巴斯克科学基金会）
Data-driven predictive solutions predominant in commercial applications tend to suffer from biases and stereotypes, which raises equity concerns. Prediction models may discover, use, or amplify spurious correlations based on gender or other protected personal characteristics, thus discriminating against marginalized groups. Mitigating gender bias has become an important research focus in natural language processing (NLP) and is an area where annotated corpora are available. Data augmentation reduces gender bias by adding counterfactual examples to the training dataset. In this work, we show th…
Fairness-Aware Streaming Feature Selection with Causal Graphs
Center for Advance Computer Studies, University of Louisiana（路易斯安那大学高级计算机研究中心）；Old Dominion University（奥多明尼昂大学）；College of Computer and Information Science, Southwest University（西南大学计算机与信息科学学院）；School of Data Science, William & Mary（威廉玛丽学院数据科学学院）
