large language models

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

Background 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...

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...

Large language models for literature screening in conceptually complex and interdisciplinary reviews

It is suggested that current LLMs can support literature screening, but their reliability depends strongly on the conceptual clarity of the review task and the structure of eligibility criteria, as well as practical implications for the transparent and responsible use of LLMs in informetric research and systematic revi...

Automated Evaluation Methods for Open-Ended Question in Hydropower Domain Based on Large Language Models

Large Language Models for Clinical Note Simplification: A Systematic Review and Experimental Evaluation of Medical Text Readability.

The findings suggest that conventional readability metrics should be extended with domain-specific measures to more accurately assess comprehensibility in medical texts and that large Language Models show strong potential to enhance the accessibility of clinical documentation for patients.

Exercise-based cardiac rehabilitation and health-related quality of life in coronary artery disease: a systematic review and meta-analysis by exercise modality and disease status

Exercise-based cardiac rehabilitation may improve health-related quality of life (HR-QoL) in patients with coronary artery disease (CAD), but whether responses differ by exercise modality and baseline disease status remains uncertain. We searched four English- and Chinese-language databases through September 2025 for r...

Introducing Synthetic Psychology: Validation Across Personality and Established Relationships.

This research introduces Synthetic Psychology (SP), a novel research approach in which large language models are configured to generate responses as synthetic individuals with predetermined psychological profiles. Across four studies with 20 replications, we configured Llama 3.3 as 32 distinct Big Five personality prof...

GarmentSketch: Large-Scale Sketch-to-Fashion Benchmark

Intention-like representations in language models?

Abstract A growing chorus of AI researchers and philosophers posit internal representations in large language models (LLMs). But how do these representations relate to the kinds of mental states we routinely ascribe to our fellow humans? While some research has focused on belief- or knowledge-like states in LLMs, there...

In-Context Molecular Property Prediction with LLMs: A Blinding Study on Memorization and Knowledge Conflicts

Abstract The capabilities of large language models (LLMs) have expanded beyond natural language processing to scientific prediction tasks, including molecular property prediction. However, their effectiveness in in-context learning remains ambiguous, particularly given the potential for training data contamination in w...