The Fellowship of the LLMs: Multi-Model Workflows for Synthetic Preference Optimization Dataset Generation
Lahore University of Management Sciences(拉合尔管理科学大学);University of Michigan - Ann Arbor(密歇根大学安娜堡分校);EMBL European Bioinformatics Institute(欧洲生物信息学研究所);Strategize Inc(Strategize公司)
Samee Arif, Sualeha Farid, Abdul Hameed Azeemi, Awais Athar, Agha Ali Raza
This paper presents a novel methodology for generating synthetic Preference Optimization (PO) datasets using multi-model workflows. We evaluate the effectiveness and potential of these workflows in automating and enhancing the dataset generation process. PO dataset generation requires two modules: (1) $\textit{response evaluation}$, and (2) $\textit{response generation}$. In the $\textit{response evaluation}$ module, the responses from Large Language Models (LLMs) are evaluated and ranked - a task typically carried out by human annotators that we automate using LLMs. We assess the response evaluation module in a 2 step process. In step 1, we assess LLMs as evaluators using three distinct prompting strategies. In step 2, we apply the winning prompting strategy to compare the performance of LLM-as-a-Judge, LLMs-as-a-Jury, and LLM Debate. Our evaluation shows that GPT-4o-as-a-Judge is more consistent across all datasets. For the $\textit{response generation}$ module, we use the identified LLM evaluator configuration and compare different configurations of the LLM Feedback Loop. We use the win rate to determine the best multi-model configuration for generation. Experimenting with various configurations, we find that the LLM Feedback Loop, with Llama as the generator and Gemma as the reviewer, achieves a notable 71.8% and 73.8% win rate over single-model Llama and Gemma, respectively. After identifying the best configurations for both modules, we generate our PO datasets using the above pipeline.
SPOGW: a Score-based Preference Optimization method via Group-Wise comparison for workflows
Hangzhou International Innovation Institute and , Beihang University(杭州国际创新研究院和 北航);School of Artificial Intelligence, Beihang University(人工智能学院,北航);Nanyang Technological University(南洋理工大学);University of Leicester(莱斯特大学);China Mobile Communications Company Limited Research Institute(中国移动通信有限公司研究院)
From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
Department of Computer Science, Rensselaer Polytechnic Institute(伦斯勒理工学院计算机科学系);IBM Research(IBM研究院);Department of Mechanical, Aerospace, and Nuclear Engineering, Rensselaer Polytechnic Institute(伦斯勒理工学院机械、航空航天与核工程系)
How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response Drafting
Department of Computer Science, Dartmouth College(计算机科学系,达特茅斯学院);Department of Community and Family Medicine, Dartmouth Health(社区与家庭医学系,达特茅斯健康);The Dartmouth Institute, Dartmouth College(达特茅斯研究所,达特茅斯学院)
Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
Department of Machine Learning, Carnegie Mellon University, Pittsburgh, PA, USA(卡内基梅隆大学机器学习系);Department of Computer Science and Engineering, University of California San Diego, La Jolla, CA, USA(加州大学圣地亚哥分校计算机科学与工程系);Department of Computer Science, University of Virginia, Charlottesville, VA, USA(弗吉尼亚大学计算机科学系);Martian Research, San Francisco, California, USA(火星研究公司);Apart Research, San Francisco, California, USA(Apart研究公司)
Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges
University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Carnegie Mellon University(卡内基梅隆大学);Yale University(耶鲁大学);The University of Texas at Austin(德克萨斯大学奥斯汀分校)
RPRO: Ranked Preference Reinforcement Optimization for Enhancing Medical QA and Diagnostic Reasoning
Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology(计算机科学与信息工程系,台湾科技大学);Department of Systems Engineering, Stevens Institute of Technology(系统工程系,史蒂文斯理工学院);Department of Management Information Systems, National Chengchi University(管理信息系,National Chengchi University);AI Research Center, Agaruda System(Agaruda系统人工智能研究中心);Department of Computer Science, Stevens Institute of Technology(计算机科学系,史蒂文斯理工学院);Far Eastern Memorial Hospital(东部纪念医院);Smart Healthcare Interdisciplinary College, National Taipei University of Nursing and Health Sciences(智慧医疗跨领域学院,台北大学护理及健康科学学院)
$π$-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows
Shanghai Jiao Tong University(上海交通大学);Shanghai AI Laboratory(上海人工智能实验室);Fudan University(复旦大学);University of Science and Technology of China(中国科学技术大学);Peking University(北京大学);Nanjing University(南京大学);Zhejiang University(浙江大学);Tongji University(同济大学);Soochow University(苏州大学);The Chinese University of Hong Kong(香港中文大学)
MedArena: Comparing LLMs for Medicine-in-the-Wild Clinician Preferences
Department of Electrical Engineering, Stanford University(斯坦福大学电气工程系);Department of Biomedical Data Science, Stanford University(斯坦福大学生物医学数据科学系);Division of Hospital Medicine, Department of Medicine, Stanford School of Medicine(斯坦福医学院医学部住院医学科);Department of Radiology, St. Jude Children's Research Hospital(圣 Jude 儿童研究医院放射科);University of California, San Francisco(旧金山大学);Department of Pathology and Laboratory Medicine, University of Wisconsin School of Medicine and Public Health(威斯康星大学医学与公共卫生学院病理学与实验室医学系);Doximity, San Francisco, CA, USA(Doximity公司);Department of Medicine, Division of Rheumatology and Immunology, Vanderbilt University Medical Center(范德比尔特大学医学中心医学系风湿病与免疫学科);Department of Neurology, Charleston Area Medical Center(查尔斯顿医疗中心神经科);Department of Translational Medicine, Scripps Research Translational Institute(斯克里普斯研究转化研究所转化医学系);Kaiser Permanente Division of Research(凯撒医疗集团研究部)
Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists
Paul G. Allen School of Computer Science \& Engineering University of Washington Seattle WA USA;The Information School University of Washington Allen Institute for AI Seattle WA USA;Allen Institute for AI Seattle WA USA;University of Washington;Allen Institute for AI
CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences
Texas A&M University(德克萨斯A&M大学);Worcester Polytechnic Institute(沃斯特理工大学);Tohoku University(东北大学);Georgia Institute of Technology(佐治亚理工学院);NVIDIA(英伟达);UCSB(加州大学圣塔芭芭拉分校);UC Merced(加州大学默塞德分校)
TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models
Shanghai University of Finance and Economics(上海财经大学);Peking University(北京大学);University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Microsoft Research(微软研究院)
LogReasoner: Empowering LLMs with Expert-like Coarse-to-Fine Reasoning for Automated Log Analysis
Shanghai Key Laboratory of Data Science, School of Computer Science, Fudan University(上海数据科学关键实验室,计算机科学学院,复旦大学);School of Artificial Intelligence and Computer Science, Jiangnan University(人工智能与计算机科学学院,江南大学)
A Large Language Model Enhanced Conversational Recommender System
University College London(伦敦大学学院);Kuaishou Technology(快手科技);Nanyang Technology University(南洋理工大学);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所)