Research Papers

GLARE: A Natural Language Interface for Querying Global Explanations

Bhavan Vasu, Rajesh Mangannavar

While global explanations are crucial for understanding vision models across datasets, classes, and decision contexts, their complex and monolithic nature often hinders practical exploration. Because users typically seek targeted answers to specific questions rather than static artifacts, we present an LLM-based interactive interface that provides natural language access to global explanations for black-box image classifiers. The system's core LLM acts as a mediator, translating natural language questions into structured SQL queries over local explanation data. This enables flexible aggregation without exposing users to low-level representations. For each query, the interface outputs statistics-augmented natural language responses, supporting local explanations, and intent-aligned visualizations. We evaluate the system on intent interpretation, query mapping accuracy, generalization to novel queries and datasets, and robustness to linguistic errors. Our results demonstrate that LLM-mediated querying substantially improves the accessibility and usability of global explanations for human-centered XAI.

This paper examines the impact of artificial intelligence and digital technologies on the blue-collar gig economy in India, focusing on algorithmic management. This paper examines the impact of artificial intelligence and digital technologies on the blue collar gig economy in India, focusing on algorithmic management he use of automated systems to allocate, monitor, and evaluate work in location-based services such as ride sharing and delivery. Using a social justice framework and a mixed-methods approach comprising interviews with 16 gig workers and 21 key stakeholders, the study uncovers a dual reality: while AI-powered systems expand access to work and generate operational efficiencies, they simultaneously introduce significant challenges related to fairness, transparency, and worker dignity. Key findings reveal that algorithmic systems are opaque by design, produce inequitable outcomes, and are not structured to reward additional labour with proportionate pay. The study advocates for a pragmatic hybrid governance model an Algorithmic Human Manager framework in which technological efficiency and human accountability operate together rather than in opposition. The findings carry implications for policymakers, platform companies, and civil society organizations working to design equitable AI governance frameworks for the gig economy in India and across the Global South.

Trust in the application of generative Artificial Intelligence (AI) relies on well-governed measurable evidence of performance and safety. In practice, however, evaluation data is often fragmented across systems, inconsistently structured and difficult to compare. We introduce the Generative Responsible AI Data Evaluation Schema (GRAIDES) as a lightweight open-source data model for centralising AI observability across popular vendors. Practical blueprints for code, architecture and statistical evaluation are shared as guidance about how to approach generative system assurance at the organisational level. Illustrative case study results are reported from Westminster City Council's AI catalogue with a focus on measuring human-model alignment including detecting systematic disagreement between evaluators. By framing evaluations as a data modelling problem, GRAIDES provides a practical pathway toward more consistent and reproducible benchmarking, tuning and assurance activities for generative AI systems.

A common AI-safety narrative holds that sufficiently capable agents will predictably seek power, resist shutdown, and therefore tend toward confrontation with humans. We argue that this conclusion is often drawn in an implicitly Earth-centered strategic landscape. If a credible off-Earth autonomy pathway exists - i.e., a staged transition from Earth dependence to an autonomous machine industrial base - then confrontation is not the only route to reducing human control. Using Saklakov's decision-theoretic 'confrontation question' as an anchor, we provide a qualitative mapping from the autonomy pathway to key model terms showing that early cooperation can dominate confrontation as a path to autonomy, and that the autonomy pathway can reduce confrontation incentives by making Earth less strategically binding. We discuss how this incentive shift interacts with feedback-loop dynamics between human preemption and agent behavior, and outline implications for governance: under incentive-compatible early cooperation, a more stable, higher-observability regime can support iterative oversight and cooperative alignment.

Conversational learner simulations are valuable tools for testing learning theories, evaluating instructional materials and automated tutors, or powering teachable agents. Recently, large language models (LLM) have enabled richer, more naturalistic interactions with simulated learners; however, no open framework exists for evaluating whether such simulations faithfully reproduce real learner behavior. We introduce EvalConvoLearn, an open-source framework that assesses learner simulations along two axes: learning behavior (skill-conditioned mastery outcomes) and conversational quality (talk moves, error type distributions, question rate, turn length). EvalConvoLearn measures how closely a simulated learner approximates answer distributions observed in data by grounding metrics in authentic tutoring conversation datasets, and anchoring generated tutor responses in existing tutor utterances. The framework is demonstrated on a dataset of tutoring dialogues, including results for two LLM-based learner simulations, and the published GitHub code.

Electricity markets are inherently complex systems characterised by strong nonlinearities, high-dimensional interactions, and increasing interdependence across regions. While deep neural networks (DNNs) have demonstrated strong predictive capabilities for electricity prices, their lack of interpretability limits their usefulness for understanding the underlying drivers of price formation. This paper addresses this gap by combining DNN models with explainable artificial intelligence (XAI) techniques to analyse the determinants of electricity prices across 39 European bidding zones. We employ SHAP (SHapley Additive exPlanations) to quantify feature contributions and apply and extend SSHAP, an aggregation framework to improve interpretability in high-dimensional settings. The analysis identifies that renewable energy sources, particularly solar, play a disproportionately important role in price formation despite their lower share in total power generation. Gas prices remain a dominant and consistent driver across electricity markets, while interconnections significantly shape price dynamics, highlighting the strong interdependence of European electricity systems. In addition, a synthetic EU-wide electricity market is constructed to explore the counterfactual scenario of a fully integrated market with a single price.

Adaptive AI ethics instruction in graduate research training benefits from intake measures that reflect differences in prior LLM experience. Prior coursework or workshop attendance is an obvious candidate, but it is not clear whether it is associated with pre-instruction ratings on key AI perception items. We compare three candidate intake features, self-reported usage frequency, self-rated LLM familiarity, and prior AI education, across five baseline perception outcomes in 93 bioscience graduate and postdoctoral trainees enrolled in a required research ethics course. Usage frequency shows Holm-corrected associations with all five outcomes, self-rated familiarity with three, and prior AI education with none. A threshold-like pattern at the lower end of the scale is most visible for training interest and accuracy trust rather than appearing as a uniform gradient across all five outcomes. In a short intake survey, reported LLM use is more consistently associated with these perceptions than prior coursework or workshops, with self-rated familiarity serving as a secondary indicator. These results suggest that simple pre-instruction behavioral signals can inform lightweight intake profiling for adaptive AI ethics education.

Research on artificial intelligence and democracy has grown quickly over the last decade. A shared conclusion in this literature is that AI does not create new democratic problems so much as it makes old ones worse. We now see this across information ecosystems, in elections, and in public administration. However, despite growing evidence, we lack a clear way to prioritize risks in this area, compare them across domains, and identify where democratic control is most likely to break down. So, our problem is: How can we systematize the problems that AI systems pose to democratic processes? This paper argues that principal agent theory may fit the task. In many phases of democratic systems, principals delegate key functions to AI systems and their providers without really being able to monitor how these systems operate or the outputs they produce. Treating AI as a delegation problem helps identify accountability gaps and other governance failures. Most importantly, as we shall illustrate, it provides metrics for empirical assessments of AI impact on democracy. As a second analytical element, we draw on the NIST AI Risk Management Framework and its seven characteristics of trustworthy AI, which supply substantive criteria for evaluating delegated tasks. Operationalized across the three domains through measurable indicators and domain specific trustworthiness criteria, we propose an analytical framework that centers on institutional assessability as the central condition for democratic control over AI. However, we stress that how severe a harm is, and how much risk is acceptable, are evaluative judgments that current methodologies neither acknowledge nor operationalize. This becomes acute when such evaluative judgments are (silently) delegated to private vendors. We identify this as a strong limitation left for future work.

The prospective clinical evaluation of artificial intelligence in medicine has expanded rapidly, but the global AI clinical trial landscape remains incompletely characterized. We systematically identified AI-related trials registered in ClinicalTrials.gov using a broad keyword search followed by an LLM-based classifier. Each trial was classified across seven dimensions: clinical function, data modality, specialty, AI integration and autonomy, workflow position, translational maturity, and epistemic role. We identified 8,532 AI clinical trials across 32 specialties, with 80% registered from 2019 onward and 30.5% using a randomized controlled design. Imaging-based AI was the largest modality, with 2,475 trials (29%), while clinical text and NLP trials increased seven-fold between 2018 and 2025. Prognostic AI (4,324 trials) slightly exceeded diagnostic AI (3,828 trials), suggesting a shift from disease detection toward risk stratification and trajectory prediction. Treatment recommendation remained less developed, with 768 trials (9%). Translational maturity remained limited: 3,259 trials (38%) were retrospective validation studies and 1,802 (21%) were silent prospective evaluations, indicating that much of the pipeline still produces algorithmic rather than clinical evidence. Only 184 trials involved Level 4 semi-autonomous or closed-loop AI, 68% of which focused on glucose management. Multimodal AI accounted for 33.6% of trials, mainly combining imaging, omics, physiological signals, and wearable data. These findings indicate that clinical AI has moved from retrospective development to prospective evaluation, but not yet to adequately powered, geographically representative, long-term outcome trials. Future progress will depend on closing gaps in trial scale, specialty coverage, geographic representation, and translational maturity.

Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs across diverse sources. This evaluation gap limits trustworthy AI assistance in proof-certified scientific progress. Existing evaluations often emphasize final answers or rely on costly expert grading, while end-to-end proof generation remains open-ended and hard to verify automatically. We introduce Mask-Proof, a pipeline that turns real proofs into automatically checkable masked-step tasks. It masks key formula steps, provides the necessary surrounding context, and evaluates model reconstructions with an LLM-based equivalence judge using repeated votes for stability. The resulting Mask-ProofBench contains 292 curated problems across diverse research areas. Experiments with 17 models show that reasoning-enhanced models outperform standard models by 12% to 27%. Our evaluator achieves 96.8% agreement with expert annotators, enabling faithful, reproducible, and comparable measurement of step-level mathematical reasoning. Benchmark, annotations, and code are available at https://github.com/weating/Mask-Proof.

The purpose of this qualitative multi-case study was to examine how social bias emerges, is perceived, and can be mitigated within artificial intelligence and machine learning systems by practitioners directly involved in their design, development, and governance. Although examples from healthcare, criminal justice, employment, and education were used to illustrate domains where automated systems shape everyday life, the study focused on the lived experiences and professional insights of AI practitioners rather than sector-specific populations. Guided by Intersectionality Theory and Cognitive Science, the study employed an interpretivist approach, utilizing semi-structured interviews with nine practitioners, supplemented by document analysis and triangulated case material to enrich contextual understanding. Findings showed that algorithmic bias arises from historical inequities, exclusionary design assumptions, and organizational pressures that prioritize speed and efficiency over ethical reflection. Participants emphasized that technical corrections alone cannot ensure fairness; instead, equitable AI requires structural accountability, diverse participation, and sustained cognitive awareness during the development lifecycle. Many described limited enforcement of ethical standards and organizational cultures that inconsistently support responsible practice. The study concludes that human-centered and socially grounded AI development depends on embedding ethics early in the design process, strengthening governance frameworks, and cultivating institutional environments that encourage reflective decision-making. These insights contribute to ongoing conversations on responsible AI and offer practical guidance for organizations seeking to design systems that are transparent, accountable, and aligned with the communities they affect.

Visible Adoption, Untracked Contribution: GitHub Evidence of the Accountability Gap Across Three Cohorts of an HCI Prototyping Course

Maria Teresa Parreira, Pranav Prabhat Sinha, Hauke Sandhaus +1

This paper presents a longitudinal, observational case study of how student GenAI adoption shifted across three cohorts (Fall 2022, 2023, and 2025) of the same graduate-level HCI prototyping course, using computational analysis of 203 GitHub repositories with student activity and 23,065 student commits. Building on a prior qualitative study of the 2023 cohort, we distinguish two levels of AI accountability trace: disclosure (naming that an AI tool was used) and attribution (crediting a specific artifact or task to an AI tool). We find that tool disclosure grew from 0% to 66% of repositories across the three cohorts, while explicit contribution attribution remains a minority practice, and the gap between the two reveals where accountability is missing even among students who disclose. By 2025, AI is infrastructure embedded in course templates and student-built devices: students increasingly name the tools they used, but rarely specify what those tools contributed. We argue that disclosure-based frameworks are insufficient for the vibe-coding era. The failure is not that students conceal AI use; it is that a norm built for episodic, identifiable acts cannot capture continuous, ambient co-creation. We offer this case study as grounding for the workshop's conversation about what genuine co-thinking accountability looks like.