large language models

Uncovering Student Thinking from Only the Answer: A GenAI Perspective

Identifying the underlying reasoning behind a student’s response to a mathematical question is a time-intensive activity for instructors. This work seeks to answer if a Large Language Model (LLM) can be used to identify potential student thinking based solely on their final response. To evaluate the LLM’s identificatio...

From Clinical Hours to Community Impact: How Participation in a National Service Corps During Fieldwork Shapes the Professional Identity of Speech-Language Pathology Students

Purpose: Professional identity formation in the field of speech-language pathology has received limited attention, particularly regarding how sustained civic engagement experiences during graduate training shape students' understanding of their future roles, values, and responsibilities. While programs such as Teach Fo...

Mapping the role of artificial intelligence in renewable energy and the clean energy transition: a bibliometric review

This study aims to present a bibliometric analysis of research on artificial intelligence (AI) applications in renewable energy (RE) technologies and the clean energy transition, highlighting both established and emerging research themes. Data were extracted from Scopus and Web of Science using clearly docum...

The evidence challenge facing large language models in medicine

Comment on egusphere-2026-3862

Abstract. Understanding coupled World-Earth system dynamics is central to navigating the Anthropocene, yet global social and environmental systems are still predominantly modelled separately. Bidirectionally coupled models of global scale that represent both subsystems as endogenous components are increasingly develope...

Frequency-Aware Mixture-of-Experts Framework for Named Entity Recognition with Adaptive Feedback Mechanism

DIAM: A New Set of Deterministic Accessibility Metrics for User Interface Evaluation in Mobile Applications Generated by Large Language Models

Benchmarking AI Vibe Coding for Clinical Statistical Analysis: A Structured Evaluation in Pulmonary Hypertension Research.

Five current large language models could reproduce expert-validated statistical analyses from a published clinical workflow across three statistical tasks: descriptive table generation, Kaplan-Meier survival analysis, and Cox proportional hazards modelling.

Accuracy, readability, and bias of GPT-4o mini responses to oculoplastic patient questions

Purpose This cross-sectional evaluation of model outputs evaluates the accuracy, readability, transparency, objectivity, completeness, and bias of GPT-4o mini responses to common oculoplastic patient questions. Methods The study was reviewed and deemed exempt from institutional review board approval. Thirty-three quest...

Market Risk Prediction Model Based on Sentiment Factors and Deep Integration of Reinforcement Learning

Effects of Acupuncture on Sleep Quality, Psychological Status, and Neuroendocrine Biomarkers in Patients With Chronic Insomnia: A Systematic Review and Meta-Analysis

Chronic insomnia impairs daytime functioning and increases the risk of cardiovascular and psychiatric disorders. Although cognitive behavioral therapy and pharmacotherapy are conventional treatments, their use may be limited by implementation barriers and adverse effects. This study systematically evaluated the eff...

Artificial Intelligence in Assessment Design for Cantonese Education

This chapter explores how artificial intelligence reshapes assessment design in higher education, using Cantonese as a second language as a distinctive lens. Cantonese's tonal and sociolinguistic complexity provides a rigorous case for evaluating AI's role in oral proficiency testing. The discussion highlights the shif...