Research Papers

This chapter examines the sociotechnical imaginaries of Brazilian tech workers, a group often overlooked in digital labor research despite their role in designing the digital systems that shape everyday life. Grounded in the idea of sociotechnical imaginaries as collectively constructed visions that guide technology development and governance, the chapter argues that looking from the Global South helps challenge data universalism and foregrounds locally situated values, constraints, and futures. Drawing on semi-structured interviews with 26 Brazilian professionals conducted between July and December 2023, it maps how workers make sense of responsibility, bias, and power in AI and platform development. The findings highlight recurring tensions between academic and industry discourse on algorithmic bias, the limits of corporate accountability regarding user harm and surveillance, and the contested meanings of digital sovereignty, including grassroots initiatives that seek alternative technological futures aligned with marginalized communities needs.

Extensive astronomical surveys, like those conducted with the {\em Chandra} X-ray Observatory, detect hundreds of thousands of unidentified cosmic sources. Machine learning (ML) methods offer an efficient, probabilistic approach to classify them, which can be useful for making discoveries and conducting deeper studies. In earlier work, we applied the LightGBM (ML model) to classify 277,069 {\em Chandra} point sources into eight categories: active galactic nuclei (AGN), X-ray emitting stars, young stellar objects (YSO), high-mass X-ray binaries, low-mass X-ray binaries, ultraluminous X-ray sources, cataclysmic variables, and pulsars. In this work, we present the classification table of 54,770 robustly classified sources (over $3σ$ confidence), including 14,066 sources at $>4σ$ significance. To ensure classification reliability and gain a deeper insight, we investigate the multiwavelength feature relationships learned by the LightGBM model, focusing on AGNs, Stars, and YSOs. We employ Explainable Artificial Intelligence (XAI) techniques, specifically, SHapley Additive exPlanations (SHAP), to quantify the contribution of individual features and their interactions to the predicted classification probabilities. Among other things, we find infrared-optical and X-ray decision boundaries for separating AGN/Stars, and infrared-X-ray boundaries for YSOs. These results are crucial for estimating object classes even with limited multiwavelength data. This study represents one of the earliest applications of XAI to large-scale astronomical datasets, demonstrating ML models' potential for uncovering physically meaningful patterns in data in addition to classification. Finally, our publicly available, extensive, and interactive catalogue will be helpful to explore the contributions of features and their combinations in greater detail in the future.

Explainable artificial intelligence (xAI) has gained significant attention in recent years. Among other things, explainablility for deep neural networks has been a topic of intensive research due to the meteoric rise in prominence of deep neural networks and their "black-box" nature. xAI approaches can be characterized along different dimensions such as their scope (global versus local explanations) or underlying methodologies (statistic-based versus rule-based strategies). Methods generating global explanations aim to provide reasoning process applicable to all possible output classes while local explanation methods focus only on a single, specific class. SHAP (SHapley Additive exPlanations), a well-known statistical technique, identifies important features of a network. Deep neural network rule extraction method constructs IF-THEN rules that link input conditions to a class. Another approach focuses on generating counterfactuals which help explain how small changes to an input can affect the model's predictions. However, these techniques primarily focus on the input-output relationship and thus neglect the structure of the network in explanation generation. In this work, we propose xDNN(ASP), an explanation generation system for deep neural networks that provides global explanations. Given a neural network model and its training data, xDNN(ASP) extracts a logic program under answer set semantics that-in the ideal case-represents the trained model, i.e., answer sets of the extracted program correspond one-to-one to input-output pairs of the network. We demonstrate experimentally, using two synthetic datasets, that not only the extracted logic program maintains a high-level of accuracy in the prediction task, but it also provides valuable information for the understanding of the model such as the importance of features as well as the impact of hidden nodes on the prediction. The latter can be used as a guide for reducing the number of nodes used in hidden layers, i.e., providing a means for optimizing the network.

Ways in which people's opinions change are, without a doubt, subject to a rich tapestry of differing influences. Factors that affect how one arrives at an opinion reflect how they have been shaped by their environment throughout their lives, education, material status, what belief systems are they subscribed to, and what socio-economic minorities are they a part of. This already complex system is further expanded by the ever-changing nature of one's social network. It is therefore no surprise that many models have a tendency to perform best for the majority of the population and discriminating those people who are members of various marginalized groups . This bias and the study of how to counter it are subject to a rapidly developing field of Fairness in Social Network Analysis (SNA). The focus of this work is to look into how a state-of-the-art model discriminates certain minority groups and whether it is possible to reliably predict for whom it will perform worse. Moreover, is such prediction possible based solely on one's demographic or topological features? To this end, the NetSense dataset, together with a state-of-the-art CoDiNG model for opinion prediction have been employed. Our work explores how three classifier models (Demography-Based, Topology-Based, and Hybrid) perform when assessing for whom this algorithm will provide inaccurate predictions. Finally, through a comprehensive analysis of these experimental results, we identify four key patterns of algorithmic bias. Our findings suggest that no single paradigm provides the best results and that there is a real need for context-aware strategies in fairness-oriented social network analysis. We conclude that a multi-faceted approach, incorporating both individual attributes and network structures, is essential for reducing algorithmic bias and promoting inclusive decision-making.

Large Language Models (LLMs) are increasingly evaluated with input attribution methods, yet comparing such explanations remains challenging. Existing soft-perturbation faithfulness metrics, such as Soft-NC and Soft-NS, can conflate attribution quality with the number of words retained during perturbation: attribution methods with larger average scores may keep more words and therefore obtain inflated scores. To address this issue, we propose $π$-Soft-NC and $π$-Soft-NS, an evaluation framework that compares attribution methods under the same expected retaining probability, thus controlling the number of retained words. We further introduce Grad-ELLM, a gradient-based attribution method tailored to autoregressive decoder-only LLMs, which combines gradient-derived channel importance with attention-derived token importance at each decoding step. Experiments on classification and open-generation tasks with Llama and Mistral show that Grad-ELLM achieves strong comprehensiveness-oriented faithfulness under $π$-Soft-NC, while there is no dominant method under $π$-Soft-NS. Our evaluation metric serves as a rigorous framework to compare XAI methods for LLMs, which will support progress in the field.

Despite recent advances in machine learning and explainable AI, a gap remains in personalized preventive healthcare: predictions, interventions, and recommendations should be both understandable and verifiable for all stakeholders in the healthcare sector. We present a demonstration of how prototype-based learning can address these needs. Our proposed framework, ProtoPal, features both front- and back-end modes; it achieves superior quantitative performance while also providing an intuitive presentation of interventions and their simulated outcomes.

Despite the rise of data-driven software systems in the modern digital landscape, data governance under a legal framework remains a critical challenge. In India, the Digital Personal Data Protection (DPDP) Act mandates rigorous data privacy and compliance requirements, necessitating software frameworks that are both ethical and regulation-aware. From a software development perspective, traditional compliance tools often rely on hard-coded rules and static configurations, making them inflexible to dynamic policy updates or evolving legal contexts. Additionally, their monolithic architectures obscure decision-making processes, creating black-box behavior in critical governance workflows. Developing responsible AI software demands transparency, traceability, and adaptive enforcement mechanisms that make ethical decisions explainable. To address this challenge, a novel agentic framework is introduced to embed compliance logic directly into software agents that govern and adapt data policies. In this paper, the implementation focuses on the DPDP Act. The framework integrates KYU Agent and Compliance Agent for this purpose. KYU (Know-YourUser) Agent supports semantic understanding, user trustworthiness modelling and Compliance Agent uses data sensitivity reasoning within a goal-driven, agentic pipeline. The proposed framework, built using an open-sourced agentic framework and has been evaluated across ten diverse domains, including healthcare, education, and e-commerce. Its effectiveness under DPDP, measured via an Anonymization Score, demonstrates scalable, compliant data governance through masking, pseudonymization, and generalization strategies tailored to domain-specific needs. The proposed framework delivers scalable, transparent, and compliant data governance through collaborative agents, dynamic policy enforcement, and domain-aware anonymization.

Iterative Deployment Improves Planning Skills in LLMs

Augusto B. Corrêa, Yoav Gelberg, Luckeciano C. Melo +3

We show that iterative deployment of large language models (LLMs), each fine-tuned on data carefully curated by users from the previous models' deployment, can significantly change the properties of the resultant models. By testing this mechanism on various planning domains, we observe substantial improvements in planning skills, with later models displaying emergent generalization by discovering much longer plans than the initial models. We then provide theoretical analysis showing that iterative deployment effectively implements reinforcement learning (RL) training in the outer-loop (i.e. not as part of intentional model training), with an implicit reward function. The connection to RL has two important implications: first, for the field of AI safety, as the reward function entailed by repeated deployment is not defined explicitly, and could have unexpected implications to the properties of future model deployments. Second, the mechanism highlighted here can be viewed as an alternative training regime to explicit RL, relying on data curation rather than explicit rewards.

Global frameworks increasingly advocate for Responsible Artificial Intelligence (AI) in education, yet they provide limited guidance on how ethical, culturally responsive, and curriculum-aligned AI can be operationalized within functioning teacher education systems, particularly in the Global South. This study addresses this gap through the design and evaluation of GenAITEd Ghana, a context-aware, region-specific conversational AI prototype developed to support teacher education in Ghana. Guided by a Design Science Research approach, the system was developed as a school-mimetic digital infrastructure aligned with the organizational logic of Ghanaian Colleges of Education and the National Council for Curriculum and Assessment (NaCCA) framework. GenAITEd Ghana operates as a multi-agent, retrieval-augmented conversational AI that coordinates multiple models for curriculum-grounded dialogue, automatic speech recognition, voice synthesis, and multimedia interaction. Two complementary prompt pathways were embedded: system-level prompts that enforce curriculum boundaries, ethical constraints, and teacher-in-the-loop oversight, and interaction-level semi-automated prompts that structure live pedagogical dialogue through clarification, confirmation, and guided response generation. Evaluation findings show that the system effectively enacted key Responsible AI principles, including transparency, accountability, cultural responsiveness, privacy, and human oversight. Human expert evaluations further indicated that GenAITEd Ghana is pedagogically appropriate for Ghanaian teacher education, promoting student engagement while preserving educators' professional authority. Identified challenges highlight the need for continued model integration, professional development, and critical AI literacy to mitigate risks of over-reliance.

Agentic artificial intelligence systems are autonomous technologies capable of pursuing complex goals with minimal human oversight and are rapidly emerging as the next frontier in AI. While these systems promise major gains in productivity, they also raise new ethical challenges. Prior research has examined how different populations prioritize Responsible AI values, yet little is known about how practitioners actually reason through the trade-offs inherent in designing these autonomous systems. This paper investigates the ethical reasoning of AI practitioners through qualitative interviews centered on structured dilemmas in agentic AI deployment. We find that the responses of practitioners do not merely reflect value preferences but rather align with three distinct reasoning frameworks. First is a Customer-Centric framework where choices are justified by business interests, legality, and user autonomy. Second is a Design-Centric framework emphasizing technical safeguards and system constraints. Third is an Ethics-Centric framework prioritizing social good and moral responsibility beyond compliance. We argue that these frameworks offer distinct and necessary insights for navigating ethical trade-offs. Consequently, providers of agentic AI must look beyond general principles and actively manage how these diverse reasoning frameworks are represented in their decision-making processes to ensure robust ethical outcomes.

Algorithmic Bias in Lending: Evidence from a Fintech Audit

Madison Coots, Robert Bartlett, Julian Nyarko +1

Algorithmic lending has transformed the consumer credit landscape, with machine learning models commonly facilitating underwriting decisions. To comply with fair lending laws, these algorithms exclude legally protected characteristics, such as race and gender. Yet algorithmic underwriting can still inadvertently favor certain groups, prompting concerns about whether lending algorithms exhibit discriminatory behavior. Using proprietary loan-level data from a major U.S. fintech platform, we audit lending decisions across approximately 80,000 personal loans. We find that loans made to men and Black borrowers yielded lower profits than loans to other groups, suggesting that men and Black borrowers benefited from relatively favorable pricing. We trace these disparities to miscalibration in the platform's underwriting model, which overestimates risk for women and underestimates risk for Black borrowers. We then show that one could correct this miscalibration -- and the corresponding disparities -- by including race and gender in underwriting models, illustrating a tension between competing notions of fairness.

Current approaches to Explainable AI (XAI) face a "Scalability-Stability Dilemma." Post-hoc methods (e.g., LIME, SHAP) may scale easily but suffer from instability, while supervised explanation frameworks (e.g., TED) offer stability but require prohibitive human effort to label every training instance. This paper proposes a Hybrid LRR-TED framework that addresses this dilemma through a novel "Asymmetry of Discovery." When applied to customer churn prediction, we demonstrate that automated rule learners (GLRM) excel at identifying broad "Safety Nets" (retention patterns) but struggle to capture specific "Risk Traps" (churn triggers)-a phenomenon we term the Anna Karenina Principle of Churn. By initialising the explanation matrix with automated safety rules and augmenting it with a Pareto-optimal set of just four human-defined risk rules, our approach achieves 94.00% predictive accuracy. This configuration outperforms the full 8-rule manual expert baseline while reducing human annotation effort by 50%, proposing a shift in the paradigm for Human-in-the-Loop AI: moving experts from the role of "Rule Writers" to "Exception Handlers."