large language models

A Capability Maturity Model for Trustworthy Generative AI in the Public Sector

Predicting facial impressions using guided Grad-CAM and a large language model

Facial impressions are central to social interaction, shaping judgments of attractiveness, dominance, and trustworthiness. Although psychophysical research has identified factors that contribute to these impressions, computational methods, particularly deep learning, offer a complementary, data-driven identification of...

Quality and safety of large language model–generated medication review outputs in geriatric pharmacotherapy: a two-stage comparative vignette-based benchmark evaluation

These findings support supervised use of large language models and evaluation approaches that assess reasoning and prioritisation as well as target detection and should not be interpreted as evidence that one model is clinically superior in real-world practice.

On the Stability of Prompt Ranking in Large Language Model Evaluation

When AI Says "I have been in similar situations": Synthetic Lived Experience in Peer-like Caregiver Support

Caregivers often turn to online communities for informational and emotional support. In these spaces, peer supporters frequently draw on personal narratives to respond to emotionally complex caregiving situations. As large language models (LLMs) are increasingly designed as peer-like sources of support, they introduce...

What we talk to when we talk to language models

When we talk to large language models, who or what is our interlocutor? First, I address some issues about how best to characterize the interlocutor in terms of mental states. Second, I discuss questions in the philosophy of computation about what sort of AI system an LLM interlocutor might be. Third, I analyze some is...

Auditing sex/gender disparities in emergency triage with LLM-based paired comparisons

We present a domain-agnostic paired-comparison approach that uses Large Language Models (LLMs) to quantify sex/gender-related asymmetries in documented clinical decision-making. The method trains an LLM to emulate observed decisions, then evaluates sex-swapped pairs in which only sex is flipped, holding documented clin...

AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations

Multi-agent large language model simulations have the potential to model complex human behaviors and interactions. If the mechanics are set up properly, unanticipated and valuable social dynamics can surface. However, it is challenging to consistently enforce simulation mechanics while still allowing for rich and emerg...

Generative debunking of climate misinformation

Misinformation is a persistent roadblock to progress on climate change, and the ubiquitous, rapid spread of misinformation means that manual solutions are inadequate to meet the scale of the problem. While many studies have developed methods for automated detection of misinformation, the generation of effective debunki...

Open or Frontier? A Cost- and Energy-Aware Benchmark of Large Language Models for Software Vulnerability Detection

Efficiency is the robust finding: open-weight models occupy the quality-efficiency Pareto frontier in every configuration tested, and no frontier model is Pareto-optimal; no frontier model is Pareto-optimal.

The Evolving Security of the Internet of Vehicles: A Survey from Classical Machine Learning to Large Language Models, Adversarial Robustness, and Explainable AI

The Internet of Vehicles (IoV) connects vehicles, roadside infrastructure, and cloud or edge platforms to support safer and more efficient transportation. This connectivity also exposes vehicular networks to message spoofing, denial-of-service, and man-in-the-middle attacks, and to threats that target the machine-learn...

APPLICATION OF ARTIFICIAL INTELLIGENCE IN PHARMACOVIGILANCE FOR AUTOMATED ADVERSE DRUG REACTION DETECTION AND REGULATORY COMPLIANCE

Pharmacovigilance is essential for continuous monitoring of medicine safety and prevention of adverse drug reactions. Traditional pharmacovigilance approaches depend mainly on spontaneous reporting and manual evaluation, resulting in underreporting, delayed signal identification and difficulties in managing large healt...