In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models
Institute for Infocomm Research (IR), A*STAR(新加坡科技研究局信息通信研究院);CNRS(法国国家科学研究中心);IRIT(图卢兹计算机科学、建模与信息工程研究所);National University of Singapore(新加坡国立大学);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)
Ayrton San Joaquin, Bin Wang, Zhengyuan Liu, Nicholas Asher, Brian Lim, Philippe Muller, Nancy F. Chen
Despite advancements, fine-tuning Large Language Models (LLMs) remains costly due to the extensive parameter count and substantial data requirements for model generalization. Accessibility to computing resources remains a barrier for the open-source community. To address this challenge, we propose the In2Core algorithm, which selects a coreset by analyzing the correlation between training and evaluation samples with a trained model. Notably, we assess the model's internal gradients to estimate this relationship, aiming to rank the contribution of each training point. To enhance efficiency, we propose an optimization to compute influence functions with a reduced number of layers while achieving similar accuracy. By applying our algorithm to instruction fine-tuning data of LLMs, we can achieve similar performance with just 50% of the training data. Meantime, using influence functions to analyze model coverage to certain testing samples could provide a reliable and interpretable signal on the training set's coverage of those test points.
M$^2$PT: Multimodal Prompt Tuning for Zero-shot Instruction Learning
Rochester Institute of Technology(罗切斯特理工学院);U.S. Naval Research Laboratory(美国海军研究实验室);Harvard Medical School(哈佛医学院);ByteDance(字节跳动);Meta AI;Meituan(美团);University of Science and Technology of China(中国科学技术大学);Shanghai Academy of AI for Science(上海人工智能科学研究院);Fudan University(复旦大学);University of Missouri - Kansas City(密苏里大学堪萨斯城分校);University of California - Davis(加利福尼亚大学戴维斯分校)
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
University of Washington(华盛顿大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Stanford University(斯坦福大学);Georgia Institute of Technology(佐治亚理工学院);University of California, Riverside(加州大学河滨分校);Microsoft Research NYC(微软研究院纽约分部)
D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
National Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);School of Artificial Intelligence, Nanjing University(南京大学人工智能学院);Algorithm Tech, Taobao & Tmall Group of Alibaba(阿里巴巴集团算法技术部);School of Intelligence Science and Technology, Nanjing University(南京大学智能科学与技术学院)
On the Effect of Instruction Tuning Loss on Generalization
Dept. of Electrical Engineering(电气工程系);Indian Institute of Technology Delhi(印度理工学院德里);Media and Data Science Research(媒体与数据科学研究);Adobe Inc., India(Adobe公司,印度)
Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer
Carnegie Mellon University(卡内基梅隆大学);Google Research(谷歌研究院);Petuum Inc.(Petuum公司);Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);UC San Diego(加州大学圣迭戈分校)
University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Northeastern University(东北大学);University of California, Berkeley(加利福尼亚大学伯克利分校);ServiceNow Research(ServiceNow研究院);Hugging Face;Roblox;Cursor AI