SCRuB: Evaluating Social Reasoning in Large Language Models
Discover SCRuB, a new framework for assessing social concept reasoning in LLMs using rubric-based evaluation and expert comparisons.
Enhancing Agentic AI Formal Verification with Knowledge Graphs
Discover how knowledge graphs improve agentic AI formal verification by linking specs to RTL, boosting assertion synthesis and verification accuracy.
Why Automated AI Alignment Remains Extremely Challenging
Explore the critical challenges and risks in automated AI alignment and why reliable oversight and generalization are essential for AI safety.
Improving OOD Detection in Evidential Deep Learning
Explore how class cardinality impacts vacuity and OOD detection in evidential deep learning, enhancing model evaluation accuracy.
How AI and Creative Legends Boost Small Business Ads
Discover how AI and top creatives unite to craft powerful ads that elevate small businesses and drive local growth.