MiST: Understanding the Role of Mid-Stage Scientific Training in Developing Chemical Reasoning Models
MiST:理解中期科学训练在开发化学推理模型中的作用
机构 * Laboratory of Artificial Chemical Intelligence (LIAC), Institute of Chemical Sciences and Engineering (ISIC)(人工化学智能实验室(LIAC)、化学科学与工程研究所) ; National Centre of Competence in Research (NCCR) Catalysis(催化研究国家级竞争力中心) ; School of Photovoltaic and Renewable Energy engineering(光伏与可再生能源工程学院) ; School of Computer Science and Engineering(计算机科学与工程学院) ; Shanghai Artificial Intelligence Laboratory(上海人工智能实验室) ; Green Dynamics
专题命中 逻辑推理 :reasoning(title,abstract);分类 cs.LG
AI总结 MiST通过中期科学训练提升化学推理模型的潜在可解性,显著提高有机反应命名和无机材料生成任务的准确率,同时产生可解释的推理轨迹。