Research Papers

The burgeoning growth of open-sourced vision-language models (VLMs) has catalyzed a plethora of applications across diverse domains. Ensuring the transparency and interpretability of these models is critical for fostering trustworthy and responsible AI systems. In this study, our objective is to delve into the internals of VLMs to interpret the functions of individual neurons. We observe the activations of neurons with respects to the input visual tokens and text tokens, and reveal some interesting findings. Particularly, we found that there are neurons responsible for only visual or text information, or both, respectively, which we refer to them as visual neurons, text neurons, and multi-modal neurons, respectively. We build a framework that automates the explanation of neurons with the assistant of GPT-4o. Meanwhile, for visual neurons, we propose an activation simulator to assess the reliability of the explanations for visual neurons. System statistical analyses on top of one representative VLM of LLaVA, uncover the behaviors/characteristics of different categories of neurons.

The automatic detection of disinformation presents a significant challenge in the field of natural language processing. This task addresses a multifaceted societal and communication issue, which needs approaches that extend beyond the identification of general linguistic patterns through data-driven algorithms. In this research work, we hypothesise that text classification methods are not able to capture the nuances of disinformation and they often ground their decision in superfluous features. Hence, we apply a post-hoc explainability method (SHAP, SHapley Additive exPlanations) to identify spurious elements with high impact on the classification models. Our findings show that non-informative elements (e.g., URLs and emoticons) should be removed and named entities (e.g., Rwanda) should be pseudo-anonymized before training to avoid models' bias and increase their generalization capabilities. We evaluate this methodology with internal dataset and external dataset before and after applying extended data preprocessing and named entity replacement. The results show that our proposal enhances on average the performance of a disinformation classification method with external test data in 65.78% without a significant decrease of the internal test performance.

Few-shot learning (FSL) enables machine learning models to generalize effectively with minimal labeled data, making it crucial for data-scarce domains such as healthcare, robotics, and natural language processing. Despite its potential, FSL faces challenges including sensitivity to initialization, difficulty in adapting to diverse domains, and vulnerability to noisy datasets. To address these issues, this paper introduces Adaptive Few-Shot Learning (AFSL), a framework that integrates advancements in meta-learning, domain alignment, noise resilience, and multi-modal integration. AFSL consists of four key modules: a Dynamic Stability Module for performance consistency, a Contextual Domain Alignment Module for domain adaptation, a Noise-Adaptive Resilience Module for handling noisy data, and a Multi-Modal Fusion Module for integrating diverse modalities. This work also explores strategies such as task-aware data augmentation, semi-supervised learning, and explainable AI techniques to enhance the applicability and robustness of FSL. AFSL provides scalable, reliable, and impactful solutions for real-world, high-stakes domains.

Importance: Emergency department (ED) returns for mental health conditions pose a major healthcare burden, with 24-27% of patients returning within 30 days. Traditional machine learning models for predicting these returns often lack interpretability for clinical use. Objective: To assess whether integrating large language models (LLMs) with machine learning improves predictive accuracy and clinical interpretability of ED mental health return risk models. Methods: This retrospective cohort study analyzed 42,464 ED visits for 27,904 unique mental health patients at an academic medical center in the Deep South from January 2018 to December 2022. Main Outcomes and Measures: Two primary outcomes were evaluated: (1) 30-day ED return prediction accuracy and (2) model interpretability using a novel LLM-enhanced framework integrating SHAP (SHapley Additive exPlanations) values with clinical knowledge. Results: For chief complaint classification, LLaMA 3 (8B) with 10-shot learning outperformed traditional models (accuracy: 0.882, F1-score: 0.86). In SDoH classification, LLM-based models achieved 0.95 accuracy and 0.96 F1-score, with Alcohol, Tobacco, and Substance Abuse performing best (F1: 0.96-0.89), while Exercise and Home Environment showed lower performance (F1: 0.70-0.67). The LLM-based interpretability framework achieved 99% accuracy in translating model predictions into clinically relevant explanations. LLM-extracted features improved XGBoost AUC from 0.74 to 0.76 and AUC-PR from 0.58 to 0.61. Conclusions and Relevance: Integrating LLMs with machine learning models yielded modest but consistent accuracy gains while significantly enhancing interpretability through automated, clinically relevant explanations. This approach provides a framework for translating predictive analytics into actionable clinical insights.

Explaining the predictions of a deep neural network is a nontrivial task, yet high-quality explanations for predictions are often a prerequisite for practitioners to trust these models. Counterfactual explanations aim to explain predictions by finding the ''nearest'' in-distribution alternative input whose prediction changes in a pre-specified way. However, it remains an open question how to define this nearest alternative input, whose solution depends on both the domain (e.g. images, graphs, tabular data, etc.) and the specific application considered. For graphs, this problem is complicated i) by their discrete nature, as opposed to the continuous nature of state-of-the-art graph classifiers; and ii) by the node permutation group acting on the graphs. We propose a method to generate counterfactual explanations for any differentiable black-box graph classifier, utilizing a case-specific permutation equivariant graph variational autoencoder. We generate counterfactual explanations in a continuous fashion by traversing the latent space of the autoencoder across the classification boundary of the classifier, allowing for seamless integration of discrete graph structure and continuous graph attributes. We empirically validate the approach on three graph datasets, showing that our model is consistently high-performing and more robust than the baselines.

As urbanization accelerates, open spaces are increasingly recognized for their role in enhancing sustainability and well-being, yet they remain underexplored compared to built spaces. This study introduces an AI-driven framework that integrates machine learning models (MLMs) and explainable AI techniques to optimize Sky View Factor (SVF) and visibility, key spatial metrics influencing thermal comfort and perceived safety in urban spaces. Unlike global optimization methods, which are computationally intensive and impractical for localized adjustments, this framework supports incremental design improvements with lower computational costs and greater flexibility. The framework employs SHapley Adaptive Explanations (SHAP) to analyze feature importance and Counterfactual Explanations (CFXs) to propose minimal design changes. Simulations tested five MLMs, identifying XGBoost as the most accurate, with building width, park area, and heights of surrounding buildings as critical for SVF, and distances from southern buildings as key for visibility. Compared to Genetic Algorithms, which required approximately 15/30 minutes across 3/4 generations to converge, the tested CFX approach achieved optimized results in 1 minute with a 5% RMSE error, demonstrating significantly faster performance and suitability for scalable retrofitting strategies. This interpretable and computationally efficient framework advances urban performance optimization, providing data-driven insights and practical retrofitting solutions for enhancing usability and environmental quality across diverse urban contexts.

Ensuring ethical behavior in Artificial Intelligence (AI) systems amidst their increasing ubiquity and influence is a major concern the world over. The use of formal methods in AI ethics is a possible crucial approach for specifying and verifying the ethical behavior of AI systems. This paper proposes a formalization based on deontic logic to define and evaluate the ethical behavior of AI systems, focusing on system-level specifications, contributing to this important goal. It introduces axioms and theorems to capture ethical requirements related to fairness and explainability. The formalization incorporates temporal operators to reason about the ethical behavior of AI systems over time. The authors evaluate the effectiveness of this formalization by assessing the ethics of the real-world COMPAS and loan prediction AI systems. Various ethical properties of the COMPAS and loan prediction systems are encoded using deontic logical formulas, allowing the use of an automated theorem prover to verify whether these systems satisfy the defined properties. The formal verification reveals that both systems fail to fulfill certain key ethical properties related to fairness and non-discrimination, demonstrating the effectiveness of the proposed formalization in identifying potential ethical issues in real-world AI applications.

This paper explores the application of Explainable AI (XAI) techniques to improve the transparency and understanding of predictive models in control of automated supply air temperature (ASAT) of Air Handling Unit (AHU). The study focuses on forecasting of ASAT using a linear regression with Huber loss. However, having only a control curve without semantic and/or physical explanation is often not enough. The present study employs one of the XAI methods: Shapley values, which allows to reveal the reasoning and highlight the contribution of each feature to the final ASAT forecast. In comparison to other XAI methods, Shapley values have solid mathematical background, resulting in interpretation transparency. The study demonstrates the contrastive explanations--slices, for each control value of ASAT, which makes it possible to give the client objective justifications for curve changes.

InclusiViz: Visual Analytics of Human Mobility Data for Understanding and Mitigating Urban Segregation

Yue Yu, Yifang Wang, Yongjun Zhang +2

Urban segregation refers to the physical and social division of people, often driving inequalities within cities and exacerbating socioeconomic and racial tensions. While most studies focus on residential spaces, they often neglect segregation across "activity spaces" where people work, socialize, and engage in leisure. Human mobility data offers new opportunities to analyze broader segregation patterns, encompassing both residential and activity spaces, but challenges existing methods in capturing the complexity and local nuances of urban segregation. This work introduces InclusiViz, a novel visual analytics system for multi-level analysis of urban segregation, facilitating the development of targeted, data-driven interventions. Specifically, we developed a deep learning model to predict mobility patterns across social groups using environmental features, augmented with explainable AI to reveal how these features influence segregation. The system integrates innovative visualizations that allow users to explore segregation patterns from broad overviews to fine-grained detail and evaluate urban planning interventions with real-time feedback. We conducted a quantitative evaluation to validate the model's accuracy and efficiency. Two case studies and expert interviews with social scientists and urban analysts demonstrated the system's effectiveness, highlighting its potential to guide urban planning toward more inclusive cities.

We propose Group Shapley, a metric that extends the classical individual-level Shapley value framework to evaluate the importance of feature groups, addressing the structured nature of predictors commonly found in business and economic data. More importantly, we develop a significance testing procedure based on a three-cumulant chi-square approximation and establish the asymptotic properties of the test statistics for Group Shapley values. Our approach can effectively handle challenging scenarios, including sparse or skewed distributions and small sample sizes, outperforming alternative tests such as the Wald test. Simulations confirm that the proposed test maintains robust empirical size and demonstrates enhanced power under diverse conditions. To illustrate the method's practical relevance in advancing Explainable AI, we apply our framework to bond recovery rate predictions using a global dataset (1996-2023) comprising 2,094 observations and 98 features, grouped into 16 subgroups and five broader categories: bond characteristics, firm fundamentals, industry-specific factors, market-related variables, and macroeconomic indicators. Our results identify the market-related variables group as the most influential. Furthermore, Lorenz curves and Gini indices reveal that Group Shapley assigns feature importance more equitably compared to individual Shapley values.

Found in Translation: semantic approaches for enhancing AI interpretability in face verification

Miriam Doh, Caroline Mazini Rodrigues, N. Boutry +3

The increasing complexity of machine learning models in computer vision, particularly in face verification, requires the development of explainable artificial intelligence (XAI) to enhance interpretability and transparency. This study extends previous work by integrating semantic concepts derived from human cognitive processes into XAI frameworks to bridge the comprehension gap between model outputs and human understanding. We propose a novel approach combining global and local explanations, using semantic features defined by user-selected facial landmarks to generate similarity maps and textual explanations via large language models (LLMs). The methodology was validated through quantitative experiments and user feedback, demonstrating improved interpretability. Results indicate that our semantic-based approach, particularly the most detailed set, offers a more nuanced understanding of model decisions than traditional methods. User studies highlight a preference for our semantic explanations over traditional pixelbased heatmaps, emphasizing the benefits of human-centric interpretability in AI. This work contributes to the ongoing efforts to create XAI frameworks that align AI models behaviour with human cognitive processes, fostering trust and acceptance in critical applications.

Intracranial hemorrhage (ICH) refers to the leakage or accumulation of blood within the skull, which occurs due to the rupture of blood vessels in or around the brain. If this condition is not diagnosed in a timely manner and appropriately treated, it can lead to serious complications such as decreased consciousness, permanent neurological disabilities, or even death.The primary aim of this study is to detect the occurrence or non-occurrence of ICH, followed by determining the type of subdural hemorrhage (SDH). These tasks are framed as two separate binary classification problems. By adding two layers to the co-scale convolutional attention (CCA) classifier architecture, we introduce a novel approach for ICH detection. In the first layer, after extracting features from different slices of computed tomography (CT) scan images, we combine these features and select the 50 components that capture the highest variance in the data, considering them as informative features. We then assess the discriminative power of these features using the bootstrap forest algorithm, discarding those that lack sufficient discriminative ability between different classes. This algorithm explicitly determines the contribution of each feature to the final prediction, assisting us in developing an explainable AI model. The features feed into a boosting neural network as a latent feature space. In the second layer, we introduce a novel uncertainty-based fuzzy integral operator to fuse information from different CT scan slices. This operator, by accounting for the dependencies between consecutive slices, significantly improves detection accuracy.