AI
SCOPE: Selective Conformal Optimized Pairwise LLM Judging
Researchers propose a framework called SCOPE for calibrating large language models (LLMs) used in pa...
AI
Adversarial Data Modeling in Epidemiology
Researchers have developed a framework to model and mitigate the effects of strategically reported d...
AI
Parametric Knowledge in RAG-SFT for Domain-Specific Document Generation
Researchers have improved document generation for electronics engineering by fine-tuning a model cal...
AI
Supporting Calibrated Reliance in Human-AI Collaboration: Different Strategies for Different Tasks
Researchers conducted three studies on human-AI collaboration. They found that different AI support ...
AI
Attention Flows: Tracing LLM Conceptual Engagement via Story Summaries
Researchers have found that large language models (LLMs) struggle to integrate i...
AI
VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning
Researchers have proposed a new framework called VISOR to improve the performanc...
AI
SegWithU: Uncertainty as Perturbation Energy for Single-Forward-Pass Risk-Aware Medical Image Segmentation
Researchers have developed a new method for medical image segmentation called Se...
AI
Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression and Catastrophic Forgetting
Researchers have developed a framework to recover performance in Large Language ...