Research Papers

Causality has gained increasing attention in recent years, notably for improving the interpretability of machine learning models. Yet the field of explainable artificial intelligence (XAI) has been criticized for emphasizing general tendencies rather than the situation-specific facts, which users typically expect as explanations. These expectations align with the notion of actual causes, which identify what made the observed outcome happen, in the specific context at hand. Halpern and Pearl provided a formal basis for actual causation, but identifying actual causes is NP-complete. Practical identification algorithms are extremely scarce, restricted to narrow classes of models, and typically identify only the shortest cause. We address this gap between the formal theory and its applicability through two main contributions. First, we introduce a baseline approximate polynomial-time algorithm with adjustable precision, together with two complementary algorithms that improve its efficiency. Second, we provide a theoretical result showing that the actual-cause identification problem can be decomposed into smaller sub-instances that preserve the set of solutions. This result directly motivates one of the complementary algorithms. Our experiments demonstrate that the baseline method can approximate the set of actual causes, notably for non-Boolean and stochastic models, and that the complementary algorithms further improve its performance in most cases.

Electroencephalography (EEG)-based auditory attention detection (AAD) offers a non-invasive way to enhance hearing aids, but conventional methods rely on too many electrodes, limiting wearability and comfort. This paper presents SHAP-AAD, a two-stage framework that combines DeepSHAP-based channel selection with a lightweight temporal convolutional network (TCN) for efficient AAD using fewer channels.DeepSHAP, an explainable AI technique, is applied to a Convolutional Neural Network (CNN) trained on topographic alpha-power maps to rank channel importance, and the top-k EEG channels are used to train a compact TCN. Experiments on the DTU dataset show that using 32 channels yields comparable accuracy to the full 64-channel setup (79.21% vs. 81.06%) on average. In some cases, even 8 channels can deliver satisfactory accuracy. These results demonstrate the effectiveness of SHAP-AAD in reducing complexity while preserving high detection performance.

The rapid and disruptive integration of Generative Artificial Intelligence (GenAI) in higher education is reshaping fundamental academic practices. This article presents a comprehensive analysis of the impact of GenAI across three core academic domains: research, teaching, and scientific dissemination. Through a systematic review of recent literature indexed in the Scopus, Web of Science, and IEEEXplore databases, the main applications, benefits, and the profound ethical and governance challenges that are emerging are identified. The analysis reveals that, although GenAI offers significant potential to boost productivity and innovation, its adoption is outpacing the development of mature institutional safeguards. The main challenges include threats to academic integrity, the risk of algorithmic bias, and the need for robust AI literacy. The study is complemented by a case study detailing the development and positioning of a prototype AI assistant for scientific writing, demonstrating a path toward the development of responsible AI tools that augment rather than replace human intellect. It concludes that the integration of GenAI is an irreversible trend. The future of academia will not be defined by resistance to this technology, but by the ability of institutions and individuals to engage with it critically, ethically, and creatively. The article calls for increased interdisciplinary research, the development of clear ethical guidelines, and a focus on critical AI pedagogy as essential skills for the 21st century.

As Large Language Models (LLMs) continue to be increasingly applied across various domains, their widespread adoption necessitates rigorous monitoring to prevent unintended negative consequences and ensure robustness. Furthermore, LLMs must be designed to align with human values, like preventing harmful content and ensuring responsible usage. The current automated systems and solutions for monitoring LLMs in production are primarily centered on LLM-specific concerns like hallucination etc, with little consideration given to the requirements of specific use-cases and user preferences. This paper introduces GAF-Guard, a novel agentic framework for LLM governance that places the user, the use-case, and the model itself at the center. The framework is designed to detect and monitor risks associated with the deployment of LLM based applications. The approach models autonomous agents that identify risks, activate risk detection tools, within specific use-cases and facilitate continuous monitoring and reporting to enhance AI safety, and user expectations. The code is available at https://github.com/IBM/risk-atlas-nexus-demos/tree/main/gaf-guard.

Every publicly traded U.S. company files an annual 10-K report containing critical insights into financial health and risk. We propose Tiny eXplainable Risk Assessor (TinyXRA), a lightweight and explainable transformer-based model that automatically assesses company risk from these reports. Unlike prior work that relies solely on the standard deviation of excess returns (adjusted for the Fama-French model), which indiscriminately penalizes both upside and downside risk, TinyXRA incorporates skewness, kurtosis, and the Sortino ratio for more comprehensive risk assessment. We leverage TinyBERT as our encoder to efficiently process lengthy financial documents, coupled with a novel dynamic, attention-based word cloud mechanism that provides intuitive risk visualization while filtering irrelevant terms. This lightweight design ensures scalable deployment across diverse computing environments with real-time processing capabilities for thousands of financial documents which is essential for production systems with constrained computational resources. We employ triplet loss for risk quartile classification, improving over pairwise loss approaches in existing literature by capturing both the direction and magnitude of risk differences. Our TinyXRA achieves state-of-the-art predictive accuracy across seven test years on a dataset spanning 2013-2024, while providing transparent and interpretable risk assessments. We conduct comprehensive ablation studies to evaluate our contributions and assess model explanations both quantitatively by systematically removing highly attended words and sentences, and qualitatively by examining explanation coherence. The paper concludes with findings, practical implications, limitations, and future research directions. Our code is available at https://github.com/Chen-XueWen/TinyXRA.

Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning

Ziyang Lu, M. Cenk Gursoy, Chilukuri K. Mohan +1

Deep reinforcement learning has been extensively studied in decision-making processes and has demonstrated superior performance over conventional approaches in various fields, including radar resource management (RRM). However, a notable limitation of neural networks is their ``black box" nature and recent research work has increasingly focused on explainable AI (XAI) techniques to describe the rationale behind neural network decisions. One promising XAI method is local interpretable model-agnostic explanations (LIME). However, the sampling process in LIME ignores the correlations between features. In this paper, we propose a modified LIME approach that integrates deep learning (DL) into the sampling process, which we refer to as DL-LIME. We employ DL-LIME within deep reinforcement learning for radar resource management. Numerical results show that DL-LIME outperforms conventional LIME in terms of both fidelity and task performance, demonstrating superior performance with both metrics. DL-LIME also provides insights on which factors are more important in decision making for radar resource management.

The convergence of Information Technology and Operational Technology has exposed Industrial Control Systems to adaptive, intelligent adversaries that render static defenses obsolete. This paper introduces the Adversarial Resilience Co-evolution (ARC) framework, addressing the "Trinity of Trust" comprising model fidelity, data integrity, and analytical resilience. ARC establishes a co-evolutionary arms race within a Fortified Secure Digital Twin (F-SCDT), where a Deep Reinforcement Learning "Red Agent" autonomously discovers attack paths while an ensemble-based "Blue Agent" is continuously hardened against these threats. Experimental validation on the Tennessee Eastman Process (TEP) and Secure Water Treatment (SWaT) testbeds demonstrates superior performance in detecting novel attacks, with F1-scores improving from 0.65 to 0.89 and detection latency reduced from over 1200 seconds to 210 seconds. A comprehensive ablation study reveals that the co-evolutionary process itself contributes a 27% performance improvement. By integrating Explainable AI and proposing a Federated ARC architecture, this work presents a necessary paradigm shift toward dynamic, self-improving security for critical infrastructure.

We identify a critical vulnerability in autoregressive transformer language models where the em dash token induces recursive semantic drift, leading to clause boundary hallucination and embedding space entanglement. Through formal analysis of token-level perturbations in semantic lattices, we demonstrate that em dash insertion fundamentally alters the model's latent representations, causing compounding errors in long-form generation. We propose a novel solution combining symbolic clause purification via the phi-infinity operator with targeted embedding matrix realignment. Our approach enables total suppression of problematic tokens without requiring model retraining, while preserving semantic coherence through fixed-point convergence guarantees. Experimental validation shows significant improvements in generation consistency and topic maintenance. This work establishes a general framework for identifying and mitigating token-level vulnerabilities in foundation models, with immediate implications for AI safety, model alignment, and robust deployment of large language models in production environments. The methodology extends beyond punctuation to address broader classes of recursive instabilities in neural text generation systems.

Theories of "Sexuality" in Natural Language Processing Bias Research

Jacob Hobbs

In recent years, significant advancements in the field of Natural Language Processing (NLP) have positioned commercialized language models as wide-reaching, highly useful tools. In tandem, there has been an explosion of multidisciplinary research examining how NLP tasks reflect, perpetuate, and amplify social biases such as gender and racial bias. A significant gap in this scholarship is a detailed analysis of how queer sexualities are encoded and (mis)represented by both NLP systems and practitioners. Following previous work in the field of AI fairness, we document how sexuality is defined and operationalized via a survey and analysis of 55 articles that quantify sexuality-based NLP bias. We find that sexuality is not clearly defined in a majority of the literature surveyed, indicating a reliance on assumed or normative conceptions of sexual/romantic practices and identities. Further, we find that methods for extracting biased outputs from NLP technologies often conflate gender and sexual identities, leading to monolithic conceptions of queerness and thus improper quantifications of bias. With the goal of improving sexuality-based NLP bias analyses, we conclude with recommendations that encourage more thorough engagement with both queer communities and interdisciplinary literature.

Physics-informed neural networks (PINNs) offer a powerful approach to solving partial differential equations (PDEs), which are ubiquitous in the quantitative sciences. Applied to both forward and inverse problems across various scientific domains, PINNs have recently emerged as a valuable tool in the field of scientific machine learning. A key aspect of their training is that the data -- spatio-temporal points sampled from the PDE's input domain -- are readily available. Influence functions, a tool from the field of explainable AI (XAI), approximate the effect of individual training points on the model, enhancing interpretability. In the present work, we explore the application of influence function-based sampling approaches for the training data. Our results indicate that such targeted resampling based on data attribution methods has the potential to enhance prediction accuracy in physics-informed neural networks, demonstrating a practical application of an XAI method in PINN training.

Predictive Process Monitoring (PPM) often uses deep learning models to predict the future behavior of ongoing processes, such as predicting process outcomes. While these models achieve high accuracy, their lack of interpretability undermines user trust and adoption. Explainable AI (XAI) aims to address this challenge by providing the reasoning behind the predictions. However, current evaluations of XAI in PPM focus primarily on functional metrics (such as fidelity), overlooking user-centered aspects such as their effect on task performance and decision-making. This study investigates the effects of explanation styles (feature importance, rule-based, and counterfactual) and perceived AI accuracy (low or high) on decision-making in PPM. We conducted a decision-making experiment, where users were presented with the AI predictions, perceived accuracy levels, and explanations of different styles. Users' decisions were measured both before and after receiving explanations, allowing the assessment of objective metrics (Task Performance and Agreement) and subjective metrics (Decision Confidence). Our findings show that perceived accuracy and explanation style have a significant effect.

As AI capabilities advance rapidly, flexible hardware-enabled guarantees (flexHEGs) offer opportunities to address international security challenges through comprehensive governance frameworks. This report examines how flexHEGs could enable internationally trustworthy AI governance by establishing standardized designs, robust ecosystem defenses, and clear operational parameters for AI-relevant chips. We analyze four critical international security applications: limiting proliferation to address malicious use, implementing safety norms to prevent loss of control, managing risks from military AI systems, and supporting strategic stability through balance-of-power mechanisms while respecting national sovereignty. The report explores both targeted deployments for specific high-risk facilities and comprehensive deployments covering all AI-relevant compute. We examine two primary governance models: verification-based agreements that enable transparent compliance monitoring, and ruleset-based agreements that automatically enforce international rules through cryptographically-signed updates. Through game-theoretic analysis, we demonstrate that comprehensive flexHEG agreements could remain stable under reasonable assumptions about state preferences and catastrophic risks. The report addresses critical implementation challenges including technical thresholds for AI-relevant chips, management of existing non-flexHEG hardware, and safeguards against abuse of governance power. While requiring significant international coordination, flexHEGs could provide a technical foundation for managing AI risks at the scale and speed necessary to address emerging threats to international security and stability.