PediaBench: a comprehensive Chinese pediatric dataset for benchmarking large language models
Peer-Reviewed Publication
Updates every hour. Last Updated: 4-Apr-2026 02:15 ET (4-Apr-2026 06:15 GMT/UTC)
Existing datasets for medical QA cannot comprehensively assess the proficiency of LLMs in pediatrics. To fill this problem, a research team led by Hui LI and Yanhao WANG published their new research on the benchmark of LLMs for pediatric QA in Frontiers of Computer Science co-published by Higher Education Press and Springer Nature.
A new economic analysis from Pandit Deendayal Energy University provides compelling evidence that financial development and digitalization are key drivers in reducing carbon dioxide emissions across six major Mediterranean countries. The research, authored by Dhyani Mehta and published in Carbon Research, examines nearly three decades of data to understand the complex relationship between economic activity and environmental impact, revealing that while some growth factors increase emissions, others offer a promising route to decarbonization.
Facial expressions serve as a crucial medium for human emotional communication. Based on duration and intensity, expressions can be categorized into macro-expressions and micro-expressions. Characterized by their involuntary and fleeting nature (lasting less than 0.5 seconds), micro-expressions (MEs) hold significant value in fields such as business negotiations, criminal investigations, and clinical diagnosis due to their uncontrollable properties.
Agricultural systems worldwide face increasing pressure to enhance productivity while mitigating environmental impact, particularly regarding greenhouse gas emissions linked to fertilizer use. The production and application of nitrogen fertilizers account for a substantial portion of agriculture's carbon footprint. Addressing this challenge, a collaborative research effort from Shenyang Agricultural University explored a novel approach: utilizing monosodium glutamate waste liquid residue (MSGWLR) as a complete or partial substitute for conventional chemical nitrogen fertilizers in rice cultivation. This investigation sought to quantify the effects on rice yield, quality parameters, and crucially, the overall carbon emissions associated with rice production, proposing a pathway toward cleaner agricultural and industrial practices.
In the field of mental health research, accurately detecting depression is crucial. However, when handling multimodal long-temporal data, two major challenges emerge: 1) Redundancy exists in long-temporal data feature extraction, and key feature extraction is unclear. 2) Existing multimodal data feature fusion methods are disrupted by inferior modality.
A University of Sydney quantum physicist has developed a new approach to quantum error correction - using lattice gauge theory - that could significantly reduce the number of physical qubits required to build large-scale, fault-tolerant quantum computers.
Observing the Taurus Molecular Cloud, a research team led by Kyushu University has found that during the early growth period of a baby star, the protostellar disk blows magnetic flux 1,000 au in size and creates a giant, relatively warm ring. Describing these phenomena as a baby star’s “sneezes,” these expulsions of energy and gas help the star to properly develop.