In this work we explore recent advances in instruction-tuning language models on a range of open instruction-following datasets. Despite recent claims that open models can be on par with state-of-the-art proprietary models, these claims are often accompanied by limited evaluation, making it difficult to compare models across the board and determine the utility of various resources. We provide a large set of instruction-tuned models from 6.7B to 65B parameters in size, trained on 12 instruction datasets ranging from manually curated (e.g., OpenAssistant) to synthetic and distilled (e.g., Alpaca) and systematically evaluate them on their factual knowledge, reasoning, multilinguality, coding, and open-ended instruction following abilities through a collection of automatic, model-based, and human-based metrics. We further introduce Tülu, our best performing instruction-tuned model suite finetuned on a combination of high-quality open resources. Our experiments show that different instruction-tuning datasets can uncover or enhance specific skills, while no single dataset (or combination) provides the best performance across all evaluations. Interestingly, we find that model and human preference-based evaluations fail to reflect differences in model capabilities exposed by benchmark-based evaluations, suggesting the need for the type of systemic evaluation performed in this work. Our evaluations show that the best model in any given evaluation reaches on average 87% of ChatGPT performance, and 73% of GPT-4 performance, suggesting that further investment in building better base models and instruction-tuning data is required to close the gap. We release our instruction-tuned models, including a fully finetuned 65B Tülu, along with our code, data, and evaluation framework at https://github.com/allenai/open-instruct to facilitate future research.
A Survey on Data Selection for LLM Instruction Tuning
Harbin Institute of Technology(哈尔滨工业大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Harbin Institute of Technology (Weihai)(哈尔滨工业大学(威海))
Exploring Large Language Models for Financial Applications: Techniques, Performance, and Challenges with FinMA
Lyman Briggs College, Michigan State University(密歇根州立大学Lyman Briggs学院);Department of Finance, Michigan State University(密歇根州立大学金融系);African Institute for Mathematical Sciences, Rwanda(刚果(金)数学科学研究所)
Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models
Mohamed Bin Zayed University of AI, UAE(穆罕默德·本·扎耶德人工智能大学,阿联酋);Khalifa University, UAE(卡比拉大学,阿联酋);Australian National University, Australia(澳大利亚国立大学,澳大利亚)
GrammarGPT: Exploring Open-Source LLMs for Native Chinese Grammatical Error Correction with Supervised Fine-Tuning
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));Soochow University(苏州大学);Shenzhen Research Institute of Big Data(深圳大数据研究院);University of Science and Technology of China(中国科学技术大学)
How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment
School of Computer Science and Technology, Beijing Institute of Technology(北京理工大学计算机科学与技术学院);Beijing Institute of Technology Southeast Academy of Information Technology(北京理工大学东南信息技术研究院)
MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments
Institute of Big Data, Fudan University(复旦大学大数据研究院);Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University(复旦大学计算机学院);School of Computer Science, Fudan University(复旦大学计算机学院);Xiaohongshu Inc.(小红书公司)
Can Frontier LLMs Replace Annotators in Biomedical Text Mining? Analyzing Challenges and Exploring Solutions
The University of Tokyo(东京大学);Graduate School of Frontier Sciences(前沿科学研究生院);Department of Computational Biology and Medical Sciences(计算生物学与医学科学系);Database Center for Life Science(生命科学数据库中心);Joint Support-Center for Data Science Research(数据科学研究联合支持中心)
Exploring LLM-based Data Annotation Strategies for Medical Dialogue Preference Alignment
School of Computer Science, Peking University(北京大学计算机学院);Key Laboratory of High Confidence Software Technologies(PKU), MOE, China(教育部高可信软件技术重点实验室(北京大学));Beijing Jiaotong University(北京交通大学)
Exploring how EFL students talk to and through AI to develop texts
Everwrite Limited(Everwrite有限公司);Shanghai Jiao Tong University(上海交通大学);The Education University of Hong Kong(香港教育大学);The University of Hong Kong(香港大学);The Chinese University of Hong Kong(香港中文大学)
Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents
Osaka University(大阪大学);Kyoto University(京都大学);University of Michigan(密歇根大学);NII(信息学研究所);Fordham University(福特汉姆大学);University of California, Los Angeles(加利福尼亚大学洛杉矶分校);University at Buffalo(布法罗大学);Nagoya University(名古屋大学)
A Multi-Modal AI Copilot for Single-Cell Analysis with Instruction Following
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);ZJU-Hangzhou Global Scientific and Technological Innovation Center(浙大杭州国际科创中心);College of Pharmaceutical Sciences, Zhejiang University(浙江大学药学院);School of Software Technology, Zhejiang University(浙江大学软件学院);Innovation Center in Zhejiang University, State Key Laboratory of Component-Based Chinese Medicine(浙江大学创新中心(国家中药复方重点实验室))