AI Patient Materials for Pediatric Oral Health Fail Standard Readability Benchmarks
A comparative study of six artificial intelligence chatbots found their pediatric oral health materials consistently exceeded recommended reading levels.
Tag: Large Language Models
Graph AI System Predicts Urban Walkability in Mexico City
A new graph machine learning framework integrates LLMs and human oversight to predict urban walkability and simulate design interventions in ...
Nine Large Language Models Evaluated on Professional Parkinson’s Disease Clinical Tasks
A benchmark evaluation of nine large language models across 200 professional Parkinson's disease tasks revealed minimal separation in factual accuracy ...
AI scans global news for chemical threats, but radiological signals prove too rare to test
A zero-shot evaluation of GPT-4o found strong performance for chemical incident extraction from news articles, while radiological events were too ...
How Generative Artificial Intelligence Is Transforming Spatial-Temporal Data Mining
A comprehensive survey analyzes how generative artificial intelligence models are transforming spatial-temporal data mining by replacing traditional deterministic networks with ...
Research report: From structured analysis to normative decision-making: a comparative evaluation of large language models in clinical ethics consultation
While the models produced well-organized documents that identified key clinical and social dimensions, the study found that high analytical scores ...
Research report: Explaining alignment between LLM classifications of political arguments and human judgments
A study of Swiss referendum debates reveals that large language models align with human evaluations of political arguments through surface ...
Vignette Study Compares AI Models and Physicians in Tuberculosis Clinical Tasks
An exploratory vignette study found that large language models matched physicians in tuberculosis diagnostic accuracy while scoring higher on structured ...
Politus Dataset Tracks Turkish Political Opinion Using Privacy-Preserving AI
Researchers have introduced the Politus Dataset, combining social media data and privacy-preserving artificial intelligence to evaluate political public opinion and ...
Router-Driven Multi-Agent Artificial Intelligence Automates Geotechnical Foundation Engineering Calculations
A router-based multi-agent artificial intelligence framework demonstrated improved accuracy and consistency over standalone frontier language models in preliminary engineering calculations ...
Compact Local Language Models Direct Robotic Drawing Arm Without Cloud Computing
Researchers have demonstrated a fully on-device robotic drawing framework that translates natural language scene descriptions into physical sketch trajectories using ...
Biomedical Knowledge Integration Enhances Language Model Cell Annotation in Single-Cell Sequencing
A computational workflow named CELLIA pairs statistical differential expression metrics with curated marker databases to improve the accuracy and consistency ...
Multimodal AI Polling Protocol Forecasts US Election Outcomes via Social Media
A multimodal language model protocol accurately predicted 50 of 51 state outcomes in the 2024 US presidential election using social ...
Review Explores Human Supervised Decision Architecture for Smart Semiconductor Manufacturing
Researchers synthesize cross layer semiconductor manufacturing controls into an auditable closed loop framework balancing classical optimization with emerging intelligent systems.
Review Finds Artificial Intelligence Depression Detection Performance Drops In Large Studies
A narrative review reveals that artificial intelligence tools for detecting depression show marked performance declines when evaluated in large cohorts ...
AI Reasoning Processes Consistently Reproduce Human Stereotypes, Study Finds
A study in Nature Machine Intelligence reveals that advanced reasoning models consistently expend greater computational effort when processing counter-stereotypical associations.
Robots that learn from each other could transform disaster rescue, review finds
A structured narrative review maps how human-to-machine, machine-to-machine and machine-to-human learning could enable collaborative search and rescue robotics while exposing ...
Collaborative LLM Agents Turn Multimodal Forensic Data Into Fraud Evidence
A new processing service called SAGE uses collaborative large language model agents to classify, transcribe and fuse multimodal forensic records, ...
Editorial Highlights Science and Clinical Applications of Total Body PET
A new Frontiers in Nuclear Medicine editorial gathers six studies showing how long axial field of view total body PET ...
Birding science takes flight across Africa as citizen data reshapes conservation
A new Frontiers in Bird Science collection shows how birding, citizen science and artificial intelligence are driving evidence-based conservation across ...
POPULAR NEWS
-
Four Social Support Profiles Emerge Among Migrant Older Adults, Study Finds
-
Younger Alzheimer’s patients carry heavier, faster-spreading tau burden, PET study finds
-
Electric toothbrush generates its own power to fight plaque bacteria
-
ASPM mutations derail human neural stem cells and explain microcephaly sensitivity