AI pinpoints and explains smart contract flaws at function level
Researchers at JAIST built a graph neural network and explanation framework that locates smart contract vulnerabilities at the individual function ...
Tag: Large Language Models
The Invisible Consultation: How Patient-Initiated AI Chats Are Reshaping Breast Cancer Care Between Appointments
A multidisciplinary review argues that patient-initiated conversational AI creates an invisible parallel pathway in breast cancer care, proposing a five-step ...
Bias Detection and Fairness Auditing in Large Language Models Remain Fragmented, Review Finds
A new review in Discover Artificial Intelligence finds that bias detection and fairness auditing techniques for large language models remain ...
EPICCAD benchmark gives AI the rules behind editable engineering designs
Researchers introduce EPICCAD, a 160,501-model multimodal benchmark that pairs CAD parts with explicit geometric constraints, procedural histories and intent-aware annotations ...
Hybrid LLM and SHAP framework explains cyberbullying predictions
A study of 5,000 Turkish tweets found that SHAP offered detailed feature attributions while local LLM explanations were clearer, with ...
Conceptual review links LLM interactions to knowledge narrowing risk
A conceptual review proposes that bounded context, ranked synthesis and iterative interaction can narrow the knowledge considered in LLM-based decision-making ...
Diabetes AI combines knowledge graphs with language models for traceable answers
A diabetes question-answering prototype combines a structured medical knowledge graph, guideline retrieval and a large language model while exposing the ...
AI is rewriting social engineering, from phishing defenses to autonomous machine deception
A new editorial synthesizing ten studies argues that artificial intelligence is transforming social engineering from human-devised deception into an AI-mediated ...
AI drug recommendations converge on the same few brand-name medicines, study finds
A large-scale evaluation of five large language models found that drug recommendations collapse onto a single product in nearly every ...
AI platform identifies synergistic drug combination for resistant prostate cancer
A UCLA artificial intelligence platform paired with three-dimensional tumor testing identified berberine and enzalutamide as a synergistic combination in four ...
Expert analysis of LLM hantavirus outbreak responses finds 11.1% potentially misleading
An expert-rated analysis of 900 responses from ChatGPT, Gemini and Claude found that 88.9% were correct or mostly correct, while ...
As Intelligent Machines Reshape Work and Information, Expert Urges Planning Now
A fortieth-anniversary editorial in AI & Society argues that AI's displacement of jobs and its grip on information demand coordinated ...
MyGPT: Open-Source AI Platform Brings Private, Local Knowledge Search to Sensitive Data
Researchers describe MyGPT, a fully open-source retrieval-augmented generation platform that runs locally or in secure environments and cites its sources ...
BERT neural network maps regional synergy in China’s ice-snow economy
A BERT-based framework combining about 12,000 consumer reviews with statistical data from 15 regional nodes identified Harbin as the absolute ...
Hybrid Optimizer Lifts AraBERT Accuracy in Arabic Sentiment Analysis
A hybrid metaheuristic algorithm combining the Aquila Optimizer, the Sine Cosine Hyperbolic Optimizer, and opposition-based learning tuned eight hyperparameters of ...
New Auditing Framework Exposes Reliability Gaps in AI-Powered First-Aid Search Results
A closed-loop auditing framework called RADAR-FirstAid reveals that Google's AI Overviews and Featured Snippets score below 0.76 on safety and ...
Research report: AI-generated high-intensity interval training information: a cross-sectional comparative evaluation of quality and readability
A standardized evaluation of 56 chatbot responses to 14 real search queries about high-intensity interval training found that Perplexity received ...
ResCity-LLM Pipeline Turns Urban Resilience Knowledge Into Specialized AI Models
Researchers built ResCity-LLM, a pipeline that turns fragmented urban resilience literature into specialized language models whose best adapted version outscored ...
Ancient Chinese Preventive Medicine Meets AI in Proposed Digital Health Framework
Researchers propose a testable framework that pairs Traditional Chinese Medicine's preventive-treatment doctrine with digital phenotyping and dual-engine AI analysis for ...
AI and a Chat Interface Team Up to Predict Wind Turbine Failures in Real Time
Researchers in Türkiye have combined IoT sensors, gradient-boosted machine learning, and a safely grounded large language model into a prototype ...
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