3

Between Help and Harm: An Evaluation of Mental Health Crisis Handling by LLMs

This work evaluates how LLMs handle mental health crises, introducing a unified taxonomy, benchmark dataset, and expert-based evaluation protocol — revealing both support capabilities and significant safety risks.

Oversmoothing, Oversquashing, Heterophily, Long-Range, and more: Demystifying Common Beliefs in Graph Machine Learning

Debates on oversmoothing, oversquashing, homophily/heterophily, and long-range tasks are muddled within each topic (e.g., oversquashing actually covers two distinct issues) so the paper urges the community to tease apart and precisely define these sub-problems.