Recent research has focused on enhancing the capability of smaller models through imitation learning, drawing on the outputs generated by large foundation models (LFMs). A number of issues impact the quality of these models, ranging from limited imitation signals from shallow LFM outputs; small scale homogeneous training data; and most notably a lack of rigorous evaluation resulting in overestimating the small model's capability as they tend to learn to imitate the style, but not the reasoning process of LFMs. To address these challenges, we develop Orca (We are working with our legal team to publicly release a diff of the model weights in accordance with LLaMA's release policy to be published at https://aka.ms/orca-lm), a 13-billion parameter model that learns to imitate the reasoning process of LFMs. Orca learns from rich signals from GPT-4 including explanation traces; step-by-step thought processes; and other complex instructions, guided by teacher assistance from ChatGPT. To promote this progressive learning, we tap into large-scale and diverse imitation data with judicious sampling and selection. Orca surpasses conventional state-of-the-art instruction-tuned models such as Vicuna-13B by more than 100% in complex zero-shot reasoning benchmarks like Big-Bench Hard (BBH) and 42% on AGIEval. Moreover, Orca reaches parity with ChatGPT on the BBH benchmark and shows competitive performance (4 pts gap with optimized system message) in professional and academic examinations like the SAT, LSAT, GRE, and GMAT, both in zero-shot settings without CoT; while trailing behind GPT-4. Our research indicates that learning from step-by-step explanations, whether these are generated by humans or more advanced AI models, is a promising direction to improve model capabilities and skills.
A Comparative Study of Open-Source Large Language Models, GPT-4 and Claude 2: Multiple-Choice Test Taking in Nephrology
Pepperdine University(佩珀代因大学);Keck Data Science Institute(凯克数据科学研究所);David Geffen School of Medicine, University of California, Los Angeles(加州大学洛杉矶分校大卫·格芬医学院);Brain Research Institute, University of California, Los Angeles(加州大学洛杉矶分校脑研究所)
DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning
Institute of Cyberspace Security, Zhejiang University of Technology A STAR Amazon Binjiang Institute of Artificial Intelligence, Zhejiang University of Technology
Quality of Answers of Generative Large Language Models vs Peer Patients for Interpreting Lab Test Results for Lay Patients: Evaluation Study
School of Information, Florida State University(佛罗里达州立大学信息学院);National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health(美国国立卫生研究院国家医学图书馆国家生物技术信息中心);Morsani College of Medicine, University of South Florida(南佛罗里达大学莫尔萨尼医学院)
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion
King Abdullah University of Science and Technology(国王阿卜杜勒阿齐兹大学科学与技术大学);Shenzhen International Center for Industrial and Applied Mathematics, Shenzhen Research Institute of Big Data(深圳国际工业与应用数学中心,深圳大数据研究院);Shenzhen Research Institute of Big Data(深圳大数据研究院);The Chinese University of Hong Kong(香港中文大学);King Abdulaziz University(国王阿卜杜勒阿齐兹大学);Prince Sattam bin Abdulaziz University(普林斯萨塔姆·本·阿卜杜勒阿齐兹大学);University of Bisha(比沙大学)
TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuning
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Baidu Inc(百度公司)
Large Language Model-Driven Dynamic Assessment of Grammatical Accuracy in English Language Learner Writing
National Institute of Standards(国家标准 institute);Department of Physics, Colorado State University(物理系,科罗拉多州立大学);Electrical Engineering Department, University of Colorado(电气工程系,科罗拉多大学)
Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection
Centre for Frontier AI Research (CFAR), A*STAR(新加坡科技研究局前沿人工智能研究中心(CFAR));Institute of High Performance Computing (IHPC), A*STAR(新加坡科技研究局高性能计算研究所(IHPC));DSO National Laboratories(DSO国家实验室)
FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insights
South China University of Technology(南方科技大学);HFIPS, Chinese Academy of Sciences(中国科学院HFIPS);University of Science and Technology of China(中国科学技术大学);The Third Affiliated Hospital of SuYat-sen University(孙逸德大学第三附属医院)
Beijing Academy of Artificial Intelligence(北京人工智能研究院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Electronic Science and Technology of China(电子科技大学);Harbin Institute of Technology, Shenzhen(哈尔滨工业大学(深圳));College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);AstralForge AI Lab(AstralForge AI实验室)