Data Selection for LLM Alignment Using Fine-Grained Preferences
利用细粒度偏好进行LLM对齐的数据选择
Jia Zhang, Yao Liu, Chen-Xi Zhang, Yi Liu, Yi-Xuan Jin, Lan-Zhe Guo, Yu-Feng Li
机构
*
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)
Cultivating Pluralism In Algorithmic Monoculture: The Community Alignment Dataset
在算法单一性中培育多元主义:社区对齐数据集
Lily Hong Zhang, Smitha Milli, Karen Jusko, Jonathan Smith, Brandon Amos, Wassim Bouaziz, Manon Revel, Jack Kussman, Yasha Sheynin, Lisa Titus, Bhaktipriya Radharapu, Jane Yu, Vidya Sarma, Kris Rose, Maximilian Nickel
机构
*
FAIR at Meta(Meta 的 FAIR 部门)
;
Governance at Meta(Meta 的治理部门)
;
AI at Meta(Meta 的人工智能部门)
;
Social Issues Research at Meta(Meta 的社会问题研究部门)
;
AI Policy Team at Meta(Meta 的人工智能政策团队)
;
Center for Data Science, New York University(纽约大学数据科学中心)
机构
*
Meta Superintelligence Labs(Meta超智能实验室)
;
Massachusetts Institute of Technology(麻省理工学院)
;
Arizona State University(亚利桑那州立大学)
;
University of Southern California(南加州大学)
How Sampling Shapes LLM Alignment: From One-Shot Optima to Iterative Dynamics
采样如何塑造大语言模型对齐:从单次最优到迭代动态
Yurong Chen, Yu He, Michael I. Jordan, Fan Yao
机构
*
Inria(法国国家信息与自动化研究所)
;
École Normale Supérieure(巴黎高等师范学校)
;
PSL Research University(巴黎综合理工研究所)
;
Northwestern University(西北大学)
;
University of California, Berkeley(加州大学伯克利分校)
;
University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)
Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment
Stackelberg 自注释:一种鲁棒的数据高效 LLM 对齐方法
Xu Chu, Zhixin Zhang, Tianyu Jia, Yujie Jin
机构
*
Key Laboratory of High Confidence Software Technologies, Ministry of Education(高可信软件技术重点实验室,教育部)
;
Center on Frontiers of Computing Studies, Peking University(计算前沿研究中心,北京大学)
;
School of Computer Science, Peking University(计算机学院,北京大学)
DA-DPO: Cost-efficient Difficulty-aware Preference Optimization for Reducing MLLM Hallucinations
DA-DPO:面向减少多模态大语言模型幻觉的高效难度感知偏好优化
Longtian Qiu, Shan Ning, Chuyu Zhang, Jiaxuan Sun, Xuming He
机构
*
ShanghaiTech University(上海科技大学)
;
Lingang Laboratory(灵冈实验室)
;
Shanghai Engineering Research Center of Intelligent Vision and Imaging(上海智能视觉与成像工程技术研究中心)
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
全栈对齐:通过厚价值模型对齐人工智能与机构
Joe Edelman, Tan Zhi-Xuan, Ryan Lowe, Oliver Klingefjord, Vincent Wang-Mascianica, Matija Franklin, Ryan Othniel Kearns, Ellie Hain, Atrisha Sarkar, Michiel Bakker, Fazl Barez, David Duvenaud, Jakob Foerster, Iason Gabriel, Joseph Gubbels, Bryce Goodman, Andreas Haupt, Jobst Heitzig, Julian Jara-Ettinger, Atoosa Kasirzadeh, James Ravi Kirkpatrick, Andrew Koh, W. Bradley Knox, Philipp Koralus, Joel Lehman, Sydney Levine, Samuele Marro, Manon Revel, Toby Shorin, Morgan Sutherland, Michael Henry Tessler, Ivan Vendrov, James Wilken-Smith
机构
*
Meaning Alignment Institute(意义对齐研究所)
;
Massachusetts Institute of Technology(麻省理工学院)
;
University College London(伦敦大学学院)
;
University of Oxford(牛津大学)
;
Western University(西方大学)
;
University of Toronto(多伦多大学)
;
McGill University(麦吉尔大学)
;
Stanford University(斯坦福大学)
;
Potsdam Institute for Climate Impact Research(波茨坦气候影响研究所)
;
Yale University(耶鲁大学)
;
Carnegie Mellon University(卡内基梅隆大学)
;
UT Austin(德克萨斯大学奥斯汀分校)
;
New York University(纽约大学)
;
Harvard University(哈佛大学)
;
Midjourney Core contributor(Midjourney核心贡献者)