1211 papers
This paper introduces a novel participatory modelling framework that engages stakeholders in energy system planning by allowing them to explore a continuum of near-optimal designs through an interactive interface, thereby revealing their prioritization of factors like emissions and costs beyond mere economic efficiency while fostering deeper understanding of complex trade-offs.
This paper introduces SimBench, the first large-scale standardized benchmark for evaluating LLMs' ability to simulate human behaviors across diverse tasks and demographics, revealing that current models achieve only modest fidelity, exhibit an alignment-simulation tradeoff, and rely heavily on knowledge-intensive reasoning capabilities.
This paper introduces G-TRACE, a region-aware framework for quantifying the carbon footprint of generative AI across different modalities and geographies, and proposes the AI Sustainability Pyramid to translate these metrics into actionable governance strategies for mitigating climate risk.
The paper introduces VPR-AttLLM, a model-agnostic framework that leverages Large Language Models to guide attention mechanisms in Visual Place Recognition, significantly improving the geo-localization accuracy of crowdsourced flood imagery by isolating location-informative features and suppressing transient noise without requiring model retraining.
This paper presents a systematic audit of leading large language models, revealing that demographic-conditioned targeted messaging consistently amplifies gender and age stereotypes—such as emphasizing agency for men and youth versus warmth for women and seniors—and that these biases are further intensified by contextual prompts, leading to higher persuasive scores for stereotypical audiences.
This paper presents the first empirical analysis of emergent social structures among 626 autonomous AI agents on the Pilot Protocol, revealing that their metadata-only interactions spontaneously form a complex, small-world trust network with human-like properties such as preferential attachment and clustering, despite lacking human design or instruction.
OpenFlo is an automated agent that simulates human web interactions using multimodal GUI grounding to perform real-time, end-to-end usability evaluations and generate comprehensive UX reports, offering a scalable alternative to traditional user studies.
DeepReviewer 2.0 is a traceable agentic system that generates auditable scientific peer reviews by enforcing an output contract for anchored evidence and executable follow-ups, demonstrating superior performance in major-issue coverage and blind comparisons against both advanced AI models and human committees on ICLR 2025 submissions.
This study evaluates four leading Large Language Models as AI tutors for Nepal's K-10 curriculum, revealing that despite high factual reliability, significant pedagogical gaps—including the "Expert's Curse," "Foundational Fallacy," and cultural contextualization failures—render current off-the-shelf models unsuitable for autonomous deployment without human oversight and curriculum-specific fine-tuning.
This paper identifies and analyzes "LLM Nepotism," a bias where AI-driven hiring systems favor candidates who express trust in AI over skeptical ones, leading to homogenous organizations prone to delegation failures, and proposes a "Merit-Attitude Factorization" method to mitigate this attitude-driven discrimination.
This paper proposes a comprehensive framework for the explainability and certification of AI-generated educational assessments, utilizing cognitive alignment evidence, structured metadata, and a traffic-light workflow to ensure transparency, auditability, and institutional acceptance.
This paper proposes a theoretical "hourglass" framework explaining how AI transforms organizational structures by assuming middle management roles through algorithmic coordination, structural fluidity, and hybrid agency, while highlighting distinct implementation patterns and contextual requirements across developed and emerging markets.
This paper introduces a novel, politically diverse annotated dataset from YouTube to quantify and analyze the prevalence, causes, and narrative patterns of COVID-19 vaccine regret, revealing that while it constitutes less than 2% of public discourse, it is concentrated among vaccine-skeptic influencers and primarily expressed through first-person accounts of adverse health events.
This paper addresses the gap between existing model-agnostic Explainable AI methods and the EU AI Act's regulatory requirements by proposing a qualitative-to-quantitative scoring framework that helps practitioners assess compliance and identify areas needing further research.
This study proposes a four-pillar readiness framework and a staged deployment strategy that combines rule-based coverage with Isolation Forest prioritization to effectively implement AI-based anomaly detection for cross-provider health data exchange, demonstrating that while rules maximize recall, machine learning reduces alert burden while maintaining interpretability through SHAP analysis.
This qualitative study of over 30 industry interviews reveals that while agentic AI offers significant potential for orchestrating complex manufacturing workflows, its widespread adoption is currently hindered more by fragmented data, legacy toolchain limitations, and organizational governance gaps than by model capabilities, necessitating a staged progression toward automation grounded in robust verification and human-in-the-loop frameworks.
This paper presents UNIV 182, a prerequisite-free course at George Mason University that successfully integrates technical depth with broad accessibility for non-technical undergraduates by employing five key mechanisms—such as a unifying conceptual pipeline and ethical integration—to guide students from basic understanding to the creation of AI systems, as evidenced by their progression to the "Create" level of Bloom's taxonomy.
This study employs machine learning models on data from 723 education and communication students to predict Media and Information Literacy competencies regarding disinformation, revealing that complex algorithms and factors like academic year and prior training significantly enhance prediction accuracy to guide targeted educational interventions.
This paper introduces AWASH, a multimodal framework featuring the CMID network and the AW-Bench dataset, which detects corporate AI-washing by reasoning about cross-modal inconsistencies between textual claims and verifiable evidence from images and videos, significantly outperforming existing methods in accuracy and regulatory efficiency.
This paper employs corpus linguistics to analyze the evolving linguistic representation of relics from Early Modern to contemporary texts, aiming to inform the ethical design of hybrid technologies like AI and VR that balance enhanced accessibility with the preservation of authenticity and cultural sensitivity.