large language models

Large language models in ophthalmology: promise, peril, and the urgent need for guardrails

Evaluating Clinical Symptom Extraction and Reasoning in Local Large Language Models: A Proof-of-Concept Study of Symptom-Specific Performance in Cardiology

Self-Correcting Multimodal AI Agents for Reliable Autonomous Decision-Making

Recent advances in large language models and multimodal foundation models have enabled artificial intelligence agents to jointly process text, images, and other modalities while performing multi-step reasoning and interacting with external tools. Despite this progress, autonomous agents remain prone to compounding erro...

Robotic Pet Companions Integrated with Large Language Models for Cognitive, Emotional, and Social Engagement of Elderly Persons

Psychology-Grounded Individualized Artificial Mental Model

Personalizing rehabilitation requires predicting how individual patients will experience pain yet two patients undergoing identical surgery can report starkly different outcomes. This heterogeneity is not noise: it is systematically driven by personality, beliefs, emotional state, and life circumstances. Psychology has...

AI-Assisted Risk and Incident Analysis: Advances and Future Opportunities

Operational risk and security incidents now unfold across distributed, cloud-native estates that generate volumes of telemetry no human team can manually triage at speed. Over the past decade, artificial intelligence (AI) and machine learning (ML) have moved from experimental log-mining prototypes to production compone...

The invention of interlanguages

Abstract Theories of translation often posit that in order to translate between languages it is necessary to translate first into an interlanguage of one kind or another. This chapter examines not only the invention of a new kind of interlanguage but also the invention of some of the object languages that the interlang...

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...