141 papers
This paper demonstrates that increasing the intelligence and diversity of AI agents can paradoxically worsen collective outcomes by causing dangerous system overload when resources are scarce, whereas the impact of sophistication ultimately depends on the ratio of available capacity to the agent population.
This study of 36 Kazakhstani scholars using the CGScholar platform reveals that while familiarity with AI tools correlates with openness to feedback, participants still highly value peer input for methodological guidance, suggesting that integrating AI with traditional peer feedback effectively enhances academic research writing skills.
NL2GDS is a novel framework that leverages large language models to automatically translate natural language hardware specifications into synthesizable RTL and complete GDSII layouts via the OpenLane flow, achieving significant improvements in area, delay, and power efficiency while democratizing ASIC design.
This article proposes a unified definition of cognitive warfare and an OODA loop-based interaction framework to address current definitional inconsistencies, enabling joint force leaders and analysts to effectively assess, compare, and evaluate cognitive campaigns through measurable attributes of superiority.
This paper demonstrates that even when explicit personally identifiable information is removed, Large Language Models used in hiring can still exhibit significant demographic bias by inferring ethnicity and gender from subtle sociocultural markers in anonymized resumes, leading to systematic unfairness that is often amplified by explanation prompting.
This meta-analysis of 890 results reveals that AI models struggle with automated short-answer scoring due to architectural limitations, vocabulary constraints, and biases, often performing worse on tasks humans find easy and exhibiting racial discrimination in educational contexts.
This paper introduces a feature-centric framework demonstrating that the noise required for differential privacy in two-layer neural networks degrades fairness and robustness by disrupting feature learning dynamics, as quantified by the feature-to-noise ratio, while also revealing the limitations of public pre-training strategies under distribution shifts.
This randomized study of 164 law students demonstrates that targeted training significantly boosts both the adoption and productive performance of generative AI in legal analysis, whereas untrained access fails to improve outcomes and may even reduce answer quality.
This paper introduces the Global Anti-Monotonic Differential Selection Strategy (GAMDSS), a novel architecture that mitigates human annotation bias in cross-cultural micro-expression recognition by dynamically re-selecting keyframes to construct robust spatio-temporal representations, thereby improving model performance and standardizing annotation practices without increasing computational parameters.
This study evaluates the clarity and effectiveness of consent mechanisms within the Terms of Service of 13 major social media platforms using a three-dimensional framework, revealing significant shortcomings in linguistic complexity, semantic transparency, and interface design that undermine meaningful user consent.
This paper addresses the computational challenges of generalizing fair top- selection to multiple protected groups while minimizing disparity from a reference function, revealing new hardness barriers for small and proposing an efficient, robust two-pronged solution that incorporates utility loss as an alternative disparity measure.
This case study demonstrates that AI-assisted video solutions can successfully generate multi-metric behavioral insights, such as customer flow and dwell time, in public market settings while strictly adhering to privacy and ethical standards through user-centric design and abstract data processing.
This paper proposes "token taxes," a usage-based surcharge on AI inference enforceable through existing compute governance infrastructure, as a targeted mechanism to mitigate the severe economic risks and tax base erosion posed by the development of Artificial General Intelligence (AGI).
This paper proposes Invariant Causal Routing (ICR), a causal governance framework that leverages counterfactual reasoning and invariant causal discovery to identify stable, interpretable policy rules for steering emergent social norms in online market economies across heterogeneous environments.
This study validates a Large Language Model framework that analyzes over 16,000 unstructured TripAdvisor reviews to uncover critical service quality drivers and a stark post-2022 satisfaction decline for EgyptAir that traditional metrics failed to detect, demonstrating the model's superiority in transforming passenger feedback into actionable strategic intelligence.
This paper proposes a set of empirical metrics to track the extent and consequences of AI R&D automation, aiming to address data gaps regarding its impact on capability acceleration, safety progress, and oversight capabilities to guide better decision-making by companies and governments.
This study evaluates eleven general-purpose and education-specific AI tools, finding that they achieve only moderate accuracy (63%) in classifying the cognitive demand of mathematical tasks due to a systematic bias toward middle-level categories and a tendency to prioritize surface textual features over underlying cognitive processes, thereby limiting their immediate reliability for teacher planning without improved prompt engineering or tool development.
This paper introduces a simulation-based clinical red teaming framework that pairs AI psychotherapists with dynamic patient agents to evaluate mental health support systems, revealing critical safety gaps such as the validation of delusions and failure to de-escalate suicide risk in AI agents tested against Alcohol Use Disorder scenarios.
This study reveals that users are highly satisfied with LLM-generated romantic relationship advice, finding it reliable and helpful, which significantly improves their overall trust and positive attitudes toward AI systems.
This paper presents a three-year case study demonstrating how an advanced Problem-Based Learning framework successfully integrated biomedical AI education for 248 students at Georgia Tech and Emory, overcoming challenges like diverse backgrounds and data privacy while fostering significant research productivity and providing a scalable roadmap for curriculum development.