The paper introduces a causal mediation framework to separate direct discrimination from structural inequality in AI-driven credit decisions. Using Pearl’s natural direct and indirect effects, it presents an identification strategy under treatment‑induced confounding and proposes a doubly‑robust estimator with efficiency guarantees. Empirical analysis of 89,465 mortgage applications shows that about 77% of racial denial disparities stem from financial mediators, while the remaining 23% represents a conservative lower bound on direct discrimination.
By Duraimurugan Rajamanickam
arXiv:2607. 05101v1 Announce Type: new Abstract: The application of machine learning-based predictive algorithms to Anti-Money Laundering (AML) has grown rapidly, driven by the vast volume of financial transaction data available to banks.
By Lea Multerer, Michele Inchingolo, David Kletz, Adrian Cosma, Alessandro Antonucci, Martina Gogova
The study investigates whether Large Language Models (LLMs) can translate technical explanations from credit risk models into stakeholder-friendly narratives. Using Freddie Mac loan data, the authors compare standard tabular models (XGBoost + SHAP) with alternative data pipelines (GNN + GNNExplainer and a bimodal mix) and generate explanations with three LLM configurations: a small fine‑tuned Gemma 3 4B, a large fine‑tuned DeepSeek R1 70B, and a zero‑shot Gemini 2.5. Findings show that the quality of explanations is more dependent on the evidence representation than on the LLM, that narratives reliably identify influential factors but are less consistent about the direction of influence, and that credit professionals demand higher evidentiary standards than non‑professionals.
By Sahab Zandi, Noah Kostesku, Christophe Mues, Mar\'ia \'Oskarsd\'ottir, Cristi\'an Bravo
The paper introduces Governance-Aware Federated Learning (GAFL), a framework that enhances traditional federated learning with independent governance verification, fairness and explainability assessment, anomaly detection, policy enforcement, and tamper‑evident audit logging. In a cross‑silo prototype with 10 participants, GAFL successfully identified all falsified‑evidence participants and intervened on affected participants across various threat scenarios, achieving macro‑F1 scores between 0.7520 and 0.7733. The added governance processing time per round was 173.67 ± 26.94 ms, compared to 3.82 ± 0.79 ms for standard FedAvg, highlighting a trade‑off between fairness policy enforcement and utility.
By Kiranmayee Janardhan, Karthick S, Madhusmita Panda, Bharathi Vokkaliga Ganesh, Syed Ahmed
arXiv:2607. 21806v1 Announce Type: new Abstract: Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice.
By Jonathan Zhang, Erik Skalnes, Jacob Chen, Michael Oberst
The paper introduces FAPE, a four‑stage framework for evaluating the post‑processing fairness intervention ThresholdOptimizer across eight diverse domains, including criminal justice, finance, healthcare, and education. It reports that the intervention reduces disparity in most high‑disparity cases but can worsen fairness when baseline disparities are low, and that a single deployment‑time audit is unreliable without continuous monitoring and baseline‑disparity screening.
By Nithin Raghava Ramachandra Narla
The paper introduces REMI, a framework that treats counterfactual fairness as a relational invariant discovery problem. By learning over paired examples, REMI identifies input regions where fairness is violated and generates interpretable rule-based models—fairness invariants—that can block or relabel unfair predictions without retraining the underlying model. Experiments on symbolic and neural network programs show REMI localizes fairness bugs in over 83% of cases and reduces discriminatory decisions in black-box models by up to 70%.
By Ranit Debnath Akash, Ashish Kumar, Gang Tan, Saeid Tizpaz-Niari
arXiv:2609.40034v1 Announce Type: cross
Abstract: Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing prediction error via Empirical Risk Minimization (ERM)...
By Ayoub Ajarra, Debabrota Basu
arXiv:2608. 00566v1 Announce Type: new Abstract: Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare.
By Niraj Kumar, Harsh Kasyap
arXiv:2609.16321v1 Announce Type: cross
Abstract: Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model dev...
By Archit Rathod, Saeid Tizpaz-Niari
CausalProfiler is a synthetic benchmark generator designed to evaluate causal machine learning (Causal ML) methods more rigorously and transparently. It randomly samples causal models, data, queries, and ground truths based on explicit design choices across observation, intervention, and counterfactual reasoning levels, providing coverage guarantees and transparent assumptions. The authors demonstrate its utility by testing several state‑of‑the‑art methods under diverse conditions, both within and outside the identification regime, highlighting the insights CausalProfiler can reveal.
By Panayiotis Panayiotou, Audrey Poinsot, Alessandro Leite, Nicolas Chesneau, Marc Schoenauer, \"Ozg\"ur \c{S}im\c{s}ek
The paper introduces Expert-Committee Audit Screening (ECAS), a framework that evaluates the credibility of synthetic minority samples for predicting crash injury severity in automated driving systems. Using real incident data from the NHTSA, ECAS filters generated samples based on label support, boundary separation, committee agreement, and local plausibility, then selects accepted samples via within‑class percentile normalization and Pareto non‑dominated sorting. The best ECAS configuration, combined with normalizing flow augmentation and a TabPFN classifier, outperformed other evidence settings in balanced accuracy, macro‑F1, and minor‑injury recall, and analysis showed ECAS‑accepted samples were better supported by nearby real crashes.
By Zewei Li, Qiaoqiao Ren, Hang Yang, S. C. Wong, Stergios-Aristoteles Mitoulis, Yun Ye