AI Is Transforming Farming, But Its Biggest Wins May Not Reach the Farmers Who Need Them Most
A sweeping review finds AI delivers impressive agricultural gains in irrigation, soil management, and pest detection, but warns that spatial ...
Tag: Large Language Models
AI Reads Crypto Whitepapers but Still Trusts the Hype Too Much
A mixed-methods study testing large language models on token-offering whitepapers finds that structured summarization with Chain-of-Thought prompting reduces rating error, ...
AI That Remembers Time: New Framework Helps Language Models Track a Deadly Lung Disease
Researchers have built a temporal-aware retrieval-augmented generation framework that helps large language models generate safer, evidence-based treatment plans for idiopathic ...
AI chatbots offer real empathy for chronic illness distress but stumble when symptoms turn serious
A standardized simulated-patient benchmarking study of ChatGPT, Gemini, and Doubao found that emotional recognition is now robust across leading AI ...
MEMOIR-VLM: an AI that reads brain scans and answers questions about Alzheimer’s disease
A new vision-language model fuses MRI, diffusion imaging and clinical scores to classify Alzheimer's disease, works even when data is ...
Tiny supervised models crush giant LLMs in fake news detection, study finds
A new benchmarking study shows that lightweight supervised embedding models dramatically outperform zero-shot and few-shot open-source large language models at ...
AI Schedules Risky Grid Maintenance When Multiple Outages Strike at Once
A large language model that forecasts load during maintenance windows helps cut cumulative outage risk from 38.1 to 2.6 on ...
AI Chatbots Flunk the Readability Test When Answering Questions About Painful Mouth Ulcers
A new study comparing five popular AI chatbots found that roughly one in ten responses about recurrent aphthous stomatitis was ...
Nursing Graduate Students Reveal the Hidden Costs and Unexpected Benefits of AI in Academia
A phenomenological study of 28 nursing graduate students in China finds that large language models ease research anxiety and language ...
AI-Made Speech Teaches Machines to Hear Estonia and Slovenia
A new study shows that synthetic speech generated by large language models significantly improves speech recognition for low-resource Estonian and ...
How Retrieval-Augmented Generation Is Rewiring What AI Knows
A new survey in Artificial Intelligence Review maps the evolution of retrieval-augmented generation from simple retrieve-then-read pipelines to agentic systems, ...
When Numbers Meet Words: Hybrid Data Representations Push Wearable Wellness AI Forward
A new study shows that how wearable sensor data is translated into language-model inputs—raw numbers, category labels, or both—critically shapes ...
Seeing Beats Remembering: What Makes a Robot Feel Socially Present
A German study comparing vision and memory in conversational Pepper robots finds that seeing enhances perceived social presence, while remembering ...
US Medical Residencies Are Flying Blind on AI Training, National Survey Finds
A national survey of internal medicine residency program directors reveals that formal education on artificial intelligence remains inconsistent across US ...
New OpenMP Code Dataset Teaches AI to Write Parallel Programs
Researchers at Emory University and Sandia National Laboratories have released a curated dataset of 77,890 OpenMP-annotated C and C++ source ...
Smartphone Pathogen Tests Get an AI Quality Gate to Cut False Alarms
Researchers propose grounded multimodal LLM interfaces as a safety-governed quality-control gate that filters noisy smartphone biosensor data before results reach ...
AI Model Reads Like a Human Brain, Tracking Hidden Cognitive States Word by Word
Researchers have built a brain-inspired model that uses a large language model to trace five hidden cognitive states as readers ...
Dual-Team AI Agents Automate and Audit Optimization Modeling
Turning a plain-English description of a logistics headache into a working mathematical model has long been a task reserved for ...
AI Health Summaries Quietly Drop Half the Medical Knowledge They Rewrite
A new study finds that large language models rewriting medical literature for patients retain only about half of the original ...
When AI Agents Get Tools, Safety Becomes an Architecture Problem
Researchers propose a five-plane software topology that separates decision, action, oversight, and adaptation to make tool-using AI agents structurally safe ...
POPULAR NEWS
-
VR Outperforms Screens for Medical Students Learning Facial Anatomy
-
Defenses Only Partially Protect Thyroid Ultrasound Segmentation From Adversarial Attacks
-
Survey Evaluates Safe Medication Practices Among Pregnant Women in Suzhou, China
-
Scoping Review Maps Cannabis-Related Emergency Visits in Youth