ChatGPT Can Predict Environmental Research Trends, but Mostly by Repeating Them
A new study found ChatGPT correctly predicted up to 80 percent of next-year research hotspots in environmental science, but achieved ...
Tag: large language models
Consistency Is Not Correctness: LLM Output Stability Fails to Predict Extraction Accuracy
A systematic evaluation of four large language models on a plant-health relation extraction benchmark finds only weak, model-dependent correlation between ...
Knowledge Graph Boosts AI Extraction of Drug Side Effects from Patient Narratives
GraphRAG-ADR combines a knowledge graph with a large language model to extract adverse drug reactions from informal patient narratives, reaching ...
AI Meets Particle Accelerators: Engineers Propose a Safety-First Integration Layer
A review by Cosylab engineers in the ARTIFACT network proposes a framework-agnostic, safety-first abstraction layer to connect AI services to ...
ChatGPT speaking practice boosts fluency and complexity in EFL learners
A ten-week study of Iranian IELTS students found ChatGPT-assisted speaking practice significantly improved syntactic complexity and speech rate, while accuracy ...
GPT-Neo Transformer Boosts Bacterial Promoter Prediction
A hybrid GPT-Neo transformer and Random Forest approach achieved 97 percent accuracy in detecting promoters in Agrobacterium tumefaciens.
Ontology-Grounded AI Tool Extracts Wetland Data with 65% Human Agreement
OntoGPT, an AI tool that grounds a large language model in scientific ontologies, agreed with human reviewers on 65 percent ...
AI Chatbots Write Safe Exercise Advice for Older Adults, but Readability Falls Short
A comparative study found that ChatGPT-4o, Claude 3.5 Sonnet, and Deepseek-R1 produced accurate, safe, fabrication-free exercise messages for older adults, ...
New Visualization Framework Explains Why Data Analysis Results Happen
Researchers have developed CAMV, a framework that automatically extracts contextual information from datasets and generates coordinated multi-view visualizations to help ...
AI Chatbots Sweep Healthcare Simulation Research, But Rigorous Outcome Studies Lag Behind
A bibliometric review of 483 studies finds large language model research in healthcare simulation education has surged since 2025, yet ...
-
Mothers who receive childcare support from maternal grandparents show more parental warmth, finds NTU Singapore study
-
University of Seville Breaks 120-Year-Old Mystery, Revises a Key Einstein Concept
-
Bee body mass, pathogens and local climate influence heat tolerance
-
Researchers record first-ever images and data of a shark experiencing a boat strike
-
Groundbreaking Clinical Trial Reveals Lubiprostone Enhances Kidney Function
Embark on a thrilling journey of discovery with Scienmag.com—your ultimate source for cutting-edge breakthroughs. Immerse yourself in a world where curiosity knows no limits and tomorrow’s possibilities become today’s reality!