AI
Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems
A team of researchers has investigated the vulnerability of clinical decision support systems to 'ga...
AI
VDGR-RAG: Vectors, Directories, Graphs, and Reflection Are All You Need for Unified Reasoning over Hierarchical Enterprise Knowledge
Researchers have developed VDGR-RAG, a unified framework for enterprise knowledge question answering...
AI
Decided Upstream, Written Late: Locating and Pricing the Cross-Lingual Refusal Circuit of a Multilingual MoE
Researchers have identified a specific circuit in a multilingual model that causes the model to refu...
AI
Rationale-Guided Learning for Multimodal Emotion Recognition
Researchers have proposed a new framework called Rationale-Guided Learning (RGL) to improve multimod...
AI
Distribird: Literature-Informed Prior Distribution Design for Bayesian Model Calibration
Researchers have developed an AI tool called Distribird that helps build informa...
AI
LLM-Guided Graph Generation for Structure-Based Local Improvement Methods
Researchers have developed a pipeline that uses large language models (LLMs) to ...
AI
The Authenticity Gap in Human Evaluation
A recent study on natural language generation (NLG) evaluation has found that th...
AI
Comprehensive framework for evaluation of deep neural networks in detection and quantification of lymphoma from PET/CT images: clinical insights, pitfalls, and observer agreement analyses
Researchers have proposed a framework for evaluating deep neural networks in det...