large language models

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...

Artificial intelligence in otolaryngology: current applications, limitations, and future perspectives.

PURPOSE Artificial intelligence (AI) is increasingly integrated into modern otolaryngology practice and has emerged as one of the most rapidly evolving technologies in contemporary medicine. Recent advances in machine learning, deep learning, computer vision, and multimodal AI systems have accelerated the development o...

Generative AI Driving the Paradigm Shift in Smart Education: Technology Layering, Application Scenarios, and Collaborative Governance

The explosive development of generative artificial intelligence is profoundly reshaping the technological pathways and application forms of smart education. Employing a narrative review methodology, this paper systematically examines the technological evolution and application trajectory of AI-empowered smart education...

Fall 2026 Environmental Sciences Seminar Series, Jingyan Huang

This seminar presents a game-based social simulation of emergency response to water contamination, in which large language model (LLM) agents represent stakeholders with diverse roles, information, incentives, and constraints. Through unfolding crisis scenario, the simulation explores how communication, coordination, a...