As tropical forests experience chronic drying and more extreme droughts due to climate change, some plants are adapting by growing longer root systems to reach water deep within soils, according to a study published in November in New Phytologist. 

University of Utah education researchers have been awarded $8 million by the Ascendium Education Group  to launch the first national center dedicated to prison education research and leadership. A team led by Erin Castro, an associate professor of educational leadership and policy, will use the grant to establish the Prison Education Action Research Lab, or PEARL, to advance educational justice for people and communities impacted by incarceration.

JMIR Publications, a leading open access publisher of digital health research, is excited to announce the upcoming second annual Society of Digital Psychiatry Symposium, a free virtual event representing a joint effort between the Society of Digital Psychiatry and JMIR Mental Health.

Mathematical reasoning is a fundamental aspect of intelligence, encompassing a spectrum from basic arithmetic to intricate problem-solving. Recent investigations into the mathematical abilities of large language models (LLMs) have yielded inconsistent and incomplete assessments. In response, we introduce MathEval, a comprehensive benchmark designed to methodically evaluate the mathematical problem-solving proficiency of LLMs in various contexts, adaptation strategies, and evaluation metrics. MathEval consolidates 22 distinct datasets, encompassing a broad spectrum of mathematical disciplines, languages (including English and Chinese), and problem categories (ranging from arithmetic and competitive mathematics to higher mathematics), with varying degrees of difficulty from elementary to advanced. To address the complexity of mathematical reasoning outputs and adapt to diverse models and prompts, we employ GPT-4 as an automated pipeline for answer extraction and comparison. Additionally, we trained a publicly available DeepSeek-LLM-7B-Base model using GPT-4 results, enabling precise answer validation without requiring GPT-4 access. To mitigate potential test data contamination and truly gauge progress, MathEval incorporates an annually refreshed set of problems from the latest Chinese National College Entrance Examination (Gaokao-2023, Gaokao-2024), thereby benchmarking genuine advancements in mathematical problem solving skills.