Research Papers

In real-world applications, computational constraints often require transforming large models into smaller, more efficient versions through model compression. While these techniques aim to reduce size and computational cost without sacrificing performance, their evaluations have traditionally focused on the trade-off between size and accuracy, overlooking the aspect of model faithfulness. This limited view is insufficient for high-stakes domains like healthcare, finance, and criminal justice, where compressed models must remain faithful to the behavior of their original counterparts. This paper presents a novel approach to evaluating faithfulness in compressed models, moving beyond standard metrics. We introduce and demonstrate a set of faithfulness metrics that capture how model behavior changes post-compression. Our contributions include introducing techniques to assess predictive consistency between the original and compressed models using model agreement, and applying chi-squared tests to detect statistically significant changes in predictive patterns across both the overall dataset and demographic subgroups, thereby exposing shifts that aggregate fairness metrics may obscure. We demonstrate our approaches by applying quantization and pruning to artificial neural networks (ANNs) trained on three diverse and socially meaningful datasets. Our findings show that high accuracy does not guarantee faithfulness, and our statistical tests detect subtle yet significant shifts that are missed by standard metrics, such as Accuracy and Equalized Odds. The proposed metrics provide a practical and more direct method for ensuring that efficiency gains through compression do not compromise the fairness or faithfulness essential for trustworthy AI.

Disclosure and Evaluation as Fairness Interventions for General-Purpose AI

Vyoma Raman, Judy Hanwen Shen, Andy K. Zhang +4

Despite conflicting definitions and conceptions of fairness, AI fairness researchers broadly agree that fairness is context-specific. However, when faced with general-purpose AI, which by definition serves a range of contexts, how should we think about fairness? We argue that while we cannot be prescriptive about what constitutes fair outcomes, we can specify the processes that different stakeholders should follow in service of fairness. Specifically, we consider the obligations of two major groups: system providers and system deployers. While system providers are natural candidates for regulatory attention, the current state of AI understanding offers limited insight into how upstream factors translate into downstream fairness impacts. Thus, we recommend that providers invest in evaluative research studying how model development decisions influence fairness and disclose whom they are serving their models to, or at the very least, reveal sufficient information for external researchers to conduct such research. On the other hand, system deployers are closer to real-world contexts and can leverage their proximity to end users to address fairness harms in different ways. Here, we argue they should responsibly disclose information about users and personalization and conduct rigorous evaluations across different levels of fairness. Overall, instead of focusing on enforcing fairness outcomes, we prioritize intentional information-gathering by system providers and deployers that can facilitate later context-aware action. This allows us to be specific and concrete about the processes even while the contexts remain unknown. Ultimately, this approach can sharpen how we distribute fairness responsibilities and inform more fluid, context-sensitive interventions as AI continues to advance.

Cross-Lingual Mental Health Ontologies for Indian Languages: Bridging Patient Expression and Clinical Understanding through Explainable AI and Human-in-the-Loop Validation

Ananth Kandala, Ratna Kandala, Akshata Kishore Moharir +2

Mental health communication in India is linguistically fragmented, culturally diverse, and often underrepresented in clinical NLP. Current health ontologies and mental health resources are dominated by diagnostic frameworks centered on English or Western culture, leaving a gap in representing patient distress expressions in Indian languages. We propose cross-linguistic graphs of patient stress expressions (CL-PDE), a framework for building cross-lingual mental health ontologies through graph-based methods that capture culturally embedded expressions of distress, align them across languages, and link them with clinical terminology. Our approach addresses critical gaps in healthcare communication by grounding AI systems in culturally valid representations, allowing more inclusive and patient-centric NLP tools for mental health care in multilingual contexts.

As Large Language Models (LLMs) gain wider adoption, ensuring their reliable handling of Personally Identifiable Information (PII) across diverse regulatory contexts has become essential. This work introduces a scalable multilingual data curation framework designed for high-quality PII annotation across 13 underrepresented locales, covering approximately 336 locale-specific PII types. Our phased, human-in-the-loop annotation methodology combines linguistic expertise with rigorous quality assurance, leading to substantial improvements in recall and false positive rates from pilot, training, and production phases. By leveraging inter-annotator agreement metrics and root-cause analysis, the framework systematically uncovers and resolves annotation inconsistencies, resulting in high-fidelity datasets suitable for supervised LLM fine-tuning. Beyond reporting empirical gains, we highlight common annotator challenges in multilingual PII labeling and demonstrate how iterative, analytics-driven pipelines can enhance both annotation quality and downstream model reliability.

The European Union's AI Act represents a crucial step towards regulating ethical and responsible AI systems. However, we find an absence of quantifiable fairness metrics and the ambiguity in terminology, particularly the interchangeable use of the keywords transparency, explainability, and interpretability in the new EU AI Act and no reference of transparency of ethical compliance. We argue that this ambiguity creates substantial liability risk that would deter investment. Fairness transparency is strategically important. We recommend a more tailored regulatory framework to enhance the new EU AI regulation. Further-more, we propose a public system framework to assess the fairness and transparency of AI systems. Drawing from past work, we advocate for the standardization of industry best practices as a necessary addition to broad regulations to achieve the level of details required in industry, while preventing stifling innovation and investment in the AI sector. The proposals are exemplified with the case of ASR and speech synthesizers.

Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment

Samuel Yeh, Sharon Li

Human feedback plays a pivotal role in aligning large language models (LLMs) with human preferences. However, such feedback is often noisy or inconsistent, which can degrade the quality of reward models and hinder alignment. While various automated data cleaning methods have been proposed to mitigate this issue, a systematic evaluation of their effectiveness and generalizability remains lacking. To bridge this gap, we introduce the first comprehensive benchmark for evaluating 13 preference data cleaning methods in the context of LLM alignment. PrefCleanBench offers a standardized protocol to assess cleaning strategies in terms of alignment performance and generalizability across diverse datasets, model architectures, and optimization algorithms. By unifying disparate methods and rigorously comparing them, we uncover key factors that determine the success of data cleaning in alignment tasks. This benchmark lays the groundwork for principled and reproducible approaches to improving LLM alignment through better data quality-highlighting the crucial but underexplored role of data preprocessing in responsible AI development. We release modular implementations of all methods to catalyze further research: https://github.com/deeplearning-wisc/PrefCleanBench.

Facial Beauty Prediction (FBP) has made significant strides with the application of deep learning, yet state-of-the-art models often exhibit critical limitations, including architectural constraints, inherent demographic biases, and a lack of transparency. Existing methods, primarily based on Convolutional Neural Networks (CNNs), excel at capturing local texture but struggle with global facial harmony, while Vision Transformers (ViTs) effectively model long-range dependencies but can miss fine-grained details. Furthermore, models trained on benchmark datasets can inadvertently learn and perpetuate societal biases related to protected attributes like ethnicity. To address these interconnected challenges, we propose \textbf{FairViT-GAN}, a novel hybrid framework that synergistically integrates a CNN branch for local feature extraction and a ViT branch for global context modeling. More significantly, we introduce an adversarial debiasing mechanism where the feature extractor is explicitly trained to produce representations that are invariant to protected attributes, thereby actively mitigating algorithmic bias. Our framework's transparency is enhanced by visualizing the distinct focus of each architectural branch. Extensive experiments on the SCUT-FBP5500 benchmark demonstrate that FairViT-GAN not only sets a new state-of-the-art in predictive accuracy, achieving a Pearson Correlation of \textbf{0.9230} and reducing RMSE to \textbf{0.2650}, but also excels in fairness. Our analysis reveals a remarkable \textbf{82.9\% reduction in the performance gap} between ethnic subgroups, with the adversary's classification accuracy dropping to near-random chance (52.1\%). We believe FairViT-GAN provides a robust, transparent, and significantly fairer blueprint for developing responsible AI systems for subjective visual assessment.

Mainstream AI ethics, with its reliance on top-down, principle-driven frameworks, fails to account for the situated realities of diverse communities affected by AI (Artificial Intelligence). Critics have argued that AI ethics frequently serves corporate interests through practices of 'ethics washing', operating more as a tool for public relations than as a means of preventing harm or advancing the common good. As a result, growing scepticism among critical scholars has cast the field as complicit in sustaining harmful systems rather than challenging or transforming them. In response, this paper adopts a Science and Technology Studies (STS) perspective to critically interrogate the field of AI ethics. It hence applies the same analytic tools STS has long directed at disciplines such as biology, medicine, and statistics to ethics. This perspective reveals a core tension between vertical (top-down, principle-based) and horizontal (risk-mitigating, implementation-oriented) approaches to ethics. By tracing how these models have shaped the discourse, we show how both fall short in addressing the complexities of AI as a socio-technical assemblage, embedded in practice and entangled with power. To move beyond these limitations, we propose a threefold reorientation of AI ethics. First, we call for a shift in foundations: from top-down abstraction to empirical grounding. Second, we advocate for pluralisation: moving beyond Western-centric frameworks toward a multiplicity of onto-epistemic perspectives. Finally, we outline strategies for reconfiguring AI ethics as a transformative force, moving from narrow paradigms of risk mitigation toward co-creating technologies of hope.

Assessing fairness in artificial intelligence (AI) typically involves AI experts who select protected features, fairness metrics, and set fairness thresholds to assess outcome fairness. However, little is known about how stakeholders, particularly those affected by AI outcomes but lacking AI expertise, assess fairness. To address this gap, we conducted a qualitative study with 26 stakeholders without AI expertise, representing potential decision subjects in a credit rating scenario, to examine how they assess fairness when placed in the role of deciding on features with priority, metrics, and thresholds. We reveal that stakeholders' fairness decisions are more complex than typical AI expert practices: they considered features far beyond legally protected features, tailored metrics for specific contexts, set diverse yet stricter fairness thresholds, and even preferred designing customized fairness. Our results extend the understanding of how stakeholders can meaningfully contribute to AI fairness governance and mitigation, underscoring the importance of incorporating stakeholders' nuanced fairness judgments.

The deployment of large language models (LLMs) in mental health and other sensitive domains raises urgent questions about ethical reasoning, fairness, and responsible alignment. Yet, existing benchmarks for moral and clinical decision-making do not adequately capture the unique ethical dilemmas encountered in mental health practice, where confidentiality, autonomy, beneficence, and bias frequently intersect. To address this gap, we introduce Ethical Reasoning in Mental Health (EthicsMH), a pilot dataset of 125 scenarios designed to evaluate how AI systems navigate ethically charged situations in therapeutic and psychiatric contexts. Each scenario is enriched with structured fields, including multiple decision options, expert-aligned reasoning, expected model behavior, real-world impact, and multi-stakeholder viewpoints. This structure enables evaluation not only of decision accuracy but also of explanation quality and alignment with professional norms. Although modest in scale and developed with model-assisted generation, EthicsMH establishes a task framework that bridges AI ethics and mental health decision-making. By releasing this dataset, we aim to provide a seed resource that can be expanded through community and expert contributions, fostering the development of AI systems capable of responsibly handling some of society's most delicate decisions.

Artificial intelligence (AI) is transforming financial planning by expanding access, lowering costs, and enabling dynamic, data-driven advice. Yet without clear safeguards, digital platforms risk reproducing longstanding market inefficiencies such as information asymmetry, misaligned incentives, and systemic fragility. This paper develops a framework for responsible AI in financial planning, anchored in five principles: fiduciary duty, adaptive personalization, technical robustness, ethical and fairness constraints, and auditability. We illustrate these risks and opportunities through case studies, and extend the framework into a five-level roadmap of AI financial intermediaries. By linking technological design to economic theory, we show how AI can either amplify vulnerabilities or create more resilient, trustworthy forms of financial intermediation.

The Quantum-Inspired Stacked Integrated Concept Graph Model (QISICGM) is an innovative machine learning framework that harnesses quantum-inspired techniques to predict diabetes risk with exceptional accuracy and efficiency. Utilizing the PIMA Indians Diabetes dataset augmented with 2,000 synthetic samples to mitigate class imbalance (total: 2,768 samples, 1,949 positives), QISICGM integrates a self-improving concept graph with a stacked ensemble comprising Random Forests (RF), Extra Trees (ET), transformers, convolutional neural networks (CNNs), and feed-forward neural networks (FFNNs). This approach achieves an out-of-fold (OOF) F1 score of 0.8933 and an AUC of 0.8699, outperforming traditional methods. Quantum inspired elements, such as phase feature mapping and neighborhood sequence modeling, enrich feature representations, enabling CPU-efficient inference at 8.5 rows per second. This paper presents a detailed architecture, theoretical foundations, code insights, and performance evaluations, including visualizations from the outputs subfolder. The open-source implementation (v1.0.0) is available at https://github.com/keninayoung/QISICGM, positioning QISICGM as a potential benchmark for AI-assisted clinical triage in diabetes and beyond. Ultimately, this work emphasizes trustworthy AI through calibration, interpretability, and open-source reproducibility.