Research Papers

Caption-Driven Explainability: Probing CNNs for Bias via CLIP

Patrick Koller, Amil V. Dravid, Guido M. Schuster +1

Robustness has become one of the most critical problems in machine learning (ML). The science of interpreting ML models to understand their behavior and improve their robustness is referred to as explainable artificial intelligence (XAI). One of the state-of-the-art XAI methods for computer vision problems is to generate saliency maps. A saliency map highlights the pixel space of an image that excites the ML model the most. However, this property could be misleading if spurious and salient features are present in overlapping pixel spaces. In this paper, we propose a caption-based XAI method, which integrates a standalone model to be explained into the contrastive language-image pre-training (CLIP) model using a novel network surgery approach. The resulting caption-based XAI model identifies the dominant concept that contributes the most to the models prediction. This explanation minimizes the risk of the standalone model falling for a covariate shift and contributes significantly towards developing robust ML models. Our code is available at https://github.com/patch0816/caption-driven-xai

AI PB: A Grounded Generative Agent for Personalized Investment Insights

Daewoo Park, Suho Park, Inseok Hong +5

We present AI PB, a production-scale generative agent deployed in real retail finance. Unlike reactive chatbots that answer queries passively, AI PB proactively generates grounded, compliant, and user-specific investment insights. It integrates (i) a component-based orchestration layer that deterministically routes between internal and external LLMs based on data sensitivity, (ii) a hybrid retrieval pipeline using OpenSearch and the finance-domain embedding model, and (iii) a multi-stage recommendation mechanism combining rule heuristics, sequential behavioral modeling, and contextual bandits. Operating fully on-premises under Korean financial regulations, the system employs Docker Swarm and vLLM across 24 X NVIDIA H100 GPUs. Through human QA and system metrics, we demonstrate that grounded generation with explicit routing and layered safety can deliver trustworthy AI insights in high-stakes finance.

Breast cancer is considered the most critical and frequently diagnosed cancer in women worldwide, leading to an increase in cancer-related mortality. Early and accurate detection is crucial as it can help mitigate possible threats while improving survival rates. In terms of prediction, conventional diagnostic methods are often limited by variability, cost, and, most importantly, risk of misdiagnosis. To address these challenges, machine learning (ML) has emerged as a powerful tool for computer-aided diagnosis, with feature selection playing a vital role in improving model performance and interpretability. This research study proposes an integrated framework that incorporates customized Particle Swarm Optimization (PSO) for feature selection. This framework has been evaluated on a comprehensive set of 29 different models, spanning classical classifiers, ensemble techniques, neural networks, probabilistic algorithms, and instance-based algorithms. To ensure interpretability and clinical relevance, the study uses cross-validation in conjunction with explainable AI methods. Experimental evaluation showed that the proposed approach achieved a superior score of 99.1\% across all performance metrics, including accuracy and precision, while effectively reducing dimensionality and providing transparent, model-agnostic explanations. The results highlight the potential of combining swarm intelligence with explainable ML for robust, trustworthy, and clinically meaningful breast cancer diagnosis.

Current methods for evaluating large language models (LLMs) typically focus on high-level tasks such as text generation, without targeting a particular AI application. This approach is not sufficient for evaluating LLMs for Responsible AI dimensions like fairness, since protected attributes that are highly relevant in one application may be less relevant in another. In this work, we construct a dataset that is driven by a real-world application (generate a plain-text product description, given a list of product features), parameterized by fairness attributes intersected with gendered adjectives and product categories, yielding a rich set of labeled prompts. We show how to use the data to identify quality, veracity, safety, and fairness gaps in LLMs, contributing a proposal for LLM evaluation paired with a concrete resource for the research community.

Public and nonprofit organizations often hesitate to adopt AI tools because most models are opaque even though standard approaches typically analyze aggregate patterns rather than offering actionable, case-level guidance. This study tests a practitioner-in-the-loop workflow that pairs transparent decision-tree models with large language models (LLMs) to improve predictive accuracy, interpretability, and the generation of practical insights. Using data from an ongoing college-success program, we build interpretable decision trees to surface key predictors. We then provide each tree's structure to an LLM, enabling it to reproduce case-level predictions grounded in the transparent models. Practitioners participate throughout feature engineering, model design, explanation review, and usability assessment, ensuring that field expertise informs the analysis at every stage. Results show that integrating transparent models, LLMs, and practitioner input yields accurate, trustworthy, and actionable case-level evaluations, offering a viable pathway for responsible AI adoption in the public and nonprofit sectors.

Recent research has focused on mitigating algorithmic bias in clustering by incorporating fairness constraints into algorithmic design. Notions such as disparate impact, community cohesion, and cost per population have been implemented to enforce equitable outcomes. Among these, group fairness (balance) ensures that each protected group is proportionally represented within every cluster. However, incorporating balance as a metric of fairness into spectral clustering algorithms has led to computational times that can be improved. This study aims to enhance the efficiency of spectral clustering algorithms by reformulating the constrained optimization problem using a new formulation derived from the Lagrangian method and the Sherman-Morrison-Woodbury (SMW) identity, resulting in the Fair-SMW algorithm. Fair-SMW employs three alternatives to the Laplacian matrix with different spectral gaps to generate multiple variations of Fair-SMW, achieving clustering solutions with comparable balance to existing algorithms while offering improved runtime performance. We present the results of Fair-SMW, evaluated using the Stochastic Block Model (SBM) to measure both runtime efficiency and balance across real-world network datasets, including LastFM, FacebookNet, Deezer, and German. We achieve an improvement in computation time that is twice as fast as the state-of-the-art, and also flexible enough to achieve twice as much balance.

The red palm mite infestation has become a serious concern, particularly in regions with extensive palm cultivation, leading to reduced productivity and economic losses. Accurate and early identification of mite-infested plants is critical for effective management. The current study focuses on evaluating and comparing the ML model for classifying the affected plants and detecting the infestation. TriggerNet is a novel interpretable AI framework that integrates Grad-CAM, RISE, FullGrad, and TCAV to generate novel visual explanations for deep learning models in plant classification and disease detection. This study applies TriggerNet to address red palm mite (Raoiella indica) infestation, a major threat to palm cultivation and agricultural productivity. A diverse set of RGB images across 11 plant species, Arecanut, Date Palm, Bird of Paradise, Coconut Palm, Ginger, Citrus Tree, Palm Oil, Orchid, Banana Palm, Avocado Tree, and Cast Iron Plant was utilized for training and evaluation. Advanced deep learning models like CNN, EfficientNet, MobileNet, ViT, ResNet50, and InceptionV3, alongside machine learning classifiers such as Random Forest, SVM, and KNN, were employed for plant classification. For disease classification, all plants were categorized into four classes: Healthy, Yellow Spots, Reddish Bronzing, and Silk Webbing. Snorkel was used to efficiently label these disease classes by leveraging heuristic rules and patterns, reducing manual annotation time and improving dataset reliability.

The Madden-Julian Oscillation (MJO) is an important driver of global weather and climate extremes, but its prediction in operational dynamical models remains challenging, with skillful forecasts typically limited to 3-4 weeks. Here, we introduce a novel deep learning framework, the Physics-guided Cascaded Corrector for MJO (PCC-MJO), which acts as a universal post-processor to correct MJO forecasts from dynamical models. This two-stage model first employs a physics-informed 3D U-Net to correct spatial-temporal field errors, then refines the MJO's RMM index using an LSTM optimized for forecast skill. When applied to three different operational forecasts from CMA, ECMWF and NCEP, our unified framework consistently extends the skillful forecast range (bivariate correlation > 0.5) by 2-8 days. Crucially, the model effectively mitigates the "Maritime Continent barrier", enabling more realistic eastward propagation and amplitude. Explainable AI analysis quantitatively confirms that the model's decision-making is spatially congruent with observed MJO dynamics (correlation > 0.93), demonstrating that it learns physically meaningful features rather than statistical fittings. Our work provides a promising physically consistent, computationally efficient, and highly generalizable pathway to break through longstanding barriers in subseasonal forecasting.

Deep Neural Networks (DNNs) are often considered black boxes due to their opaque decision-making processes. To reduce their opacity Concept Models (CMs), such as Concept Bottleneck Models (CBMs), were introduced to predict human-defined concepts as an intermediate step before predicting task labels. This enhances the interpretability of DNNs. In a human-machine setting greater interpretability enables humans to improve their understanding and build trust in a DNN. In the introduction of CBMs, the models demonstrated increased task accuracy as incorrect concept predictions were replaced with their ground truth values, known as intervening on the concept predictions. In a collaborative setting, if the model task accuracy improves from interventions, trust in a model and the human-machine task accuracy may increase. However, the result showing an increase in model task accuracy was produced without human evaluation and thus it remains unknown if the findings can be applied in a collaborative setting. In this paper, we ran the first human studies using CBMs to evaluate their human interaction in collaborative task settings. Our findings show that CBMs improve interpretability compared to standard DNNs, leading to increased human-machine alignment. However, this increased alignment did not translate to a significant increase in task accuracy. Understanding the model's decision-making process required multiple interactions, and misalignment between the model's and human decision-making processes could undermine interpretability and model effectiveness.

The increasing complexity of Beyond 5G and 6G networks necessitates new paradigms for autonomy and assur- ance. Traditional O-RAN control loops rely heavily on RIC- based orchestration, which centralizes intelligence and exposes the system to risks such as policy conflicts, data drift, and unsafe actions under unforeseen conditions. In this work, we argue that the future of autonomous networks lies in a multi-agentic architecture, where specialized agents collaborate to perform data collection, model training, prediction, policy generation, verification, deployment, and assurance. By replacing tightly- coupled centralized RIC-based workflows with distributed agents, the framework achieves autonomy, resilience, explainability, and system-wide safety. To substantiate this vision, we design and evaluate a traffic steering use case under surge and drift conditions. Results across four KPIs: RRC connected users, IP throughput, PRB utilization, and SINR, demonstrate that a naive predictor-driven deployment improves local KPIs but destabilizes neighbors, whereas the agentic system blocks unsafe policies, preserving global network health. This study highlights multi- agent architectures as a credible foundation for trustworthy AI- driven autonomy in next-generation RANs.

VoiceMorph: How AI Voice Morphing Reveals the Boundaries of Auditory Self-Recognition

Kye Shimizu, Minghan Gao, Ananya Ganesh +1

This study investigated auditory self-recognition boundaries using AI voice morphing technology, examining when individuals cease recognizing their own voice. Through controlled morphing between participants' voices and demographically matched targets at 1% increments using a mixed-methods design, we measured self-identification ratings and response times among 21 participants aged 18-64. Results revealed a critical recognition threshold at 35.2% morphing (95% CI [31.4, 38.1]). Older participants tolerated significantly higher morphing levels before losing self-recognition ($β$ = 0.617, p = 0.048), suggesting age-related vulnerabilities. Greater acoustic embedding distances predicted slower decision-making ($r \approx 0.5-0.53, p < 0.05$), with the longest response times for cloned versions of participants' own voices. Qualitative analysis revealed prosodic-based recognition strategies, universal voice manipulation discomfort, and awareness of applications spanning assistive technology to security risks. These findings establish foundational evidence for individual differences in voice morphing detection, with implications for AI ethics and vulnerable population protection as voice synthesis becomes accessible.

We introduce NAEL (Non-Anthropocentric Ethical Logic), a novel ethical framework for artificial agents grounded in active inference and symbolic reasoning. Departing from conventional, human-centred approaches to AI ethics, NAEL formalizes ethical behaviour as an emergent property of intelligent systems minimizing global expected free energy in dynamic, multi-agent environments. We propose a neuro-symbolic architecture to allow agents to evaluate the ethical consequences of their actions in uncertain settings. The proposed system addresses the limitations of existing ethical models by allowing agents to develop context-sensitive, adaptive, and relational ethical behaviour without presupposing anthropomorphic moral intuitions. A case study involving ethical resource distribution illustrates NAEL's dynamic balancing of self-preservation, epistemic learning, and collective welfare.