Information overload is a major obstacle to scientific progress. The explosive growth in scientific literature and data has made it ever harder to discover useful insights in a large mass of information. Today scientific knowledge is accessed through search engines, but they are unable to organize scientific knowledge alone. In this paper we introduce Galactica: a large language model that can store, combine and reason about scientific knowledge. We train on a large scientific corpus of papers, reference material, knowledge bases and many other sources. We outperform existing models on a range of scientific tasks. On technical knowledge probes such as LaTeX equations, Galactica outperforms the latest GPT-3 by 68.2% versus 49.0%. Galactica also performs well on reasoning, outperforming Chinchilla on mathematical MMLU by 41.3% to 35.7%, and PaLM 540B on MATH with a score of 20.4% versus 8.8%. It also sets a new state-of-the-art on downstream tasks such as PubMedQA and MedMCQA dev of 77.6% and 52.9%. And despite not being trained on a general corpus, Galactica outperforms BLOOM and OPT-175B on BIG-bench. We believe these results demonstrate the potential for language models as a new interface for science. We open source the model for the benefit of the scientific community.
Systematic Framework of Application Methods for Large Language Models in Language Sciences
Tongji University, China(同济大学);University of Tübingen, Germany(图宾根大学);Institute of Natural Language Processing, University of Stuttgart, Germany(斯图加特大学自然语言处理研究所)
GeoGalactica: A Scientific Large Language Model in Geoscience
Shanghai Jiao Tong University(上海交通大学);University of Michigan(密歇根大学);Institute of Geographical Science and Natural Resources Research, CAS(中国科学院地理科学与资源研究所);The Hong Kong University of Science and Technology(香港科技大学)
Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data
Public Policy Programme, The Alan Turing Institute, British Library(公共政策计划、艾伦·图灵研究所、大英图书馆);School of Geographical Sciences, University of Bristol(地理科学学院、布里斯托尔大学);Oxford Internet Institute, University of Oxford(牛津大学网络研究所);Zug Institute for Blockchain Research, University of Lucerne(祖格区块链研究所、卢塞恩大学)
It's not Rocket Science : Interpreting Figurative Language in Narratives
Columbia University(哥伦比亚大学);Allen Institute for Artificial Intelligence(艾伦人工智能研究所);University of Washington(华盛顿大学);University of British Columbia(不列颠哥伦比亚大学)
Prompt Selection Matters: Enhancing Text Annotations for Social Sciences with Large Language Models
Université Paris 1 Panthéon-Sorbonne(巴黎第一大学先贤祠-索邦大学);Université Paris-Saclay(巴黎萨克雷大学);Institut Jean Nicod(让·尼科德研究所);Ecole Normale Supérieure(巴黎高等师范学院);PSL-EHESS-CNRS(巴黎文理研究大学-法国高等社会科学研究院-法国国家科学研究中心)
PLLaMa: An Open-source Large Language Model for Plant Science
University of California, Santa Barbara(加州大学圣塔芭芭拉分校);University of Lincoln(林肯大学);Chinese Academy of Agricultural Sciences(中国农业科学院);Swedish University of Agricultural Sciences(瑞典农业科学大学)
Pedagogical Alignment for Vision-Language-Action Models: A Comprehensive Framework for Data, Architecture, and Evaluation in Education
Chosun University(全州大学);Seoul National University(首尔国立大学);Korea Institute for Curriculum and Evaluation(韩国课程评价院);Nanyang Technological University(南洋理工大学)
Large language models in materials science and the need for open-source approaches
School of Physics, Chemistry and Earth Sciences, The University of Adelaide(物理、化学和地球科学学院,阿德莱德大学);School of Computer and Mathematical Sciences, The University of Adelaide(计算机与数学科学学院,阿德莱德大学)
MatTools: Benchmarking Large Language Models for Materials Science Tools
Center for Structural Materials, Department of Mechanical Engineering, The University of Hong Kong(香港大学机械工程系结构材料中心);Materials Innovation Institute for Life Sciences(生命科学创新研究所)
OceanGPT: A Large Language Model for Ocean Science Tasks
College Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);Donghai Laboratory(东海实验室);School of Software Technology, Zhejiang University(浙江大学软件学院);Huzhou University(湖州大学);Ocean College, Zhejiang University(浙江大学海洋学院);Zhoushan-Zhejiang University Ocean Research Center(舟山浙江大学海洋研究中心)
BioPars: A Pretrained Biomedical Large Language Model for Persian Biomedical Text Mining
Department of Computer Science, Faculty of Education, University of Kufa(计算机科学系,教育学院,科菲大学);Department of Computer Science, Florida State University(计算机科学系,佛罗里达州立大学);Department of Computer Engineering, Velayat University(计算机工程系,瓦莱yat大学);Department of Mechanical Engineering, Amirkabir University of Technology(机械工程系,阿米卡比尔技术大学);Department of Computer Engineering, Ferdowsi University of Mashhad(计算机工程系,法尔德大学)
Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model
School of Computer Science and Engineering, University of New South Wales(新南威尔士大学计算机科学与工程学院);GreenDynamics(绿动力);Department of Materials Science and Engineering, City University of Hong Kong(香港城市大学材料科学与工程系);Department of Linguistics and Translation, City University of Hong Kong(香港城市大学语言学与翻译系);School of Photovoltaic and Renewable Energy Engineering, University of New South Wales(新南威尔士大学光伏与可再生能源工程学院);College of Design & Innovation, Tongji University(同济大学设计与创新学院)