Large language models (LLMs) exhibit impressive capabilities across a wide range of tasks, yet the choice of which model to use often involves a trade-off between performance and cost. More powerful models, though effective, come with higher expenses, while less capable models are more cost-effective. To address this dilemma, we propose several efficient router models that dynamically select between a stronger and a weaker LLM during inference, aiming to optimize the balance between cost and response quality. We develop a training framework for these routers leveraging human preference data and data augmentation techniques to enhance performance. Our evaluation on widely-recognized benchmarks shows that our approach significantly reduces costs-by over 2 times in certain cases-without compromising the quality of responses. Interestingly, our router models also demonstrate significant transfer learning capabilities, maintaining their performance even when the strong and weak models are changed at test time. This highlights the potential of these routers to provide a cost-effective yet high-performance solution for deploying LLMs.
LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences
School of Electrical and Computer Engineering, Purdue University(普渡大学电气与计算机工程学院);Department of Computer Science and Engineering, Yonsei University(延世大学计算机科学与工程系);Polytechnic Institute, Purdue University(普渡大学理工学院)
GMTRouter: Personalized LLM Router over Multi-turn User Interactions
Antiquus S. Hippocampus, Natalia Cerebro & Amelie P. Amygdale Department of Computer Science Cranberry-Lemon University Pittsburgh, PA 15213, USA(计算机科学系,Cranberry-Lemon大学);Ji Q. Ren & Yevgeny LeNet Department of Computational Neuroscience University of the Witwatersrand Joburg, South Africa(计算神经科学系,沃特瓦特斯兰大学)
ChatPlanner: A Large Language Model Framework for Personalized Public Transit Routing
School of Engineering and Materials Science, Queen Mary University of London(伦敦玛丽女王大学工程与材料科学学院);Department of Engineering Science, University of Oxford(牛津大学工程科学系)
Multi-objective Large Language Model Alignment with Hierarchical Experts
Harbin Institute of Technology, Shenzhen, China(哈尔滨工业大学(深圳));Nanyang Technological University(南洋理工大学);Peng Cheng Laboratory(鹏城实验室);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Tencent(腾讯)
PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);National University of Singapore(新加坡国立大学);Southeast University, Nanjing, China(南京东南大学);Wuhan AI Research, Wuhan, China(武汉人工智能研究院)
TraveLLM: Could you plan my new public transit route in face of a network disruption?
Department of Industrial Engineering and Operations Research, Columbia University(工业工程与运营管理系,哥伦比亚大学);Department of Civil Engineering and Engineering Mechanics, Columbia University(土木工程与工程力学系,哥伦比亚大学);Data Science Institute, Columbia University(数据科学研究院,哥伦比亚大学)
MedAlign: A Synergistic Framework of Multimodal Preference Optimization and Federated Meta-Cognitive Reasoning
School of Automation, Guangdong University of Technology(广东工业大学自动化学院);College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics(南京航空航天大学计算机科学与技术学院);State Key Laboratory of Traditional Chinese Medicine Syndrome, The Second Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangdong Provincial Hospital of Chinese Medicine, Guangdong Provincial Academy of Chinese Medical Sciences(广东省中医药科学院中医证候重点实验室,广州中医药大学第二附属医院,广东省中医院,广东省中医药科学院);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算机与数据科学学院);Department of Electrical and Computer Engineering, Sungkyunkwan University(成均馆大学电子与计算机工程系)
RAIE: Region-Aware Incremental Preference Editing with LoRA for LLM-based Recommendation
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区计算机科学与技术学院);Department of Computer Science and Technology, Xiamen University(厦门大学计算机科学与技术系);Artificial Intelligence Research Institute, Shenzhen MSU-BIT University(深圳MSU-BIT大学人工智能研究院);School of Information, Central University of Finance and Economics(中央财经大学信息学院);School of Artificial Intelligence, Beijing Normal University(北京师范大学人工智能学院)
RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing
School of Artificial Intelligence, Nanjing University(南京大学人工智能学院);National Key Laboratory for Novel Software Technology, Nanjing University(南京大学计算机软件新技术国家重点实验室);SinapisAI
Meta-Router: Bridging Gold-standard and Preference-based Evaluations in Large Language Model Routing
Department of Statistics, Indiana University Bloomington(印第安纳大学布卢明顿分校统计系);Department of Statistics, North Carolina State University(北卡罗来纳州立大学统计系);Department of Biostatistics, The University of Texas MD Anderson Cancer Center(德克萨斯大学MD安德森癌症中心生物统计学系)
Preference-Aware Delivery Planning for Last-Mile Logistics
Singapore Management University(新加坡管理大学)
最后一公里物流配送路径优化是一个具有挑战性的问题,已经引起了许多研究者的关注。这些问题通常被建模和解决为具有挑战性的现实世界约束的车辆路径问题(VRP)的变体(例如,时间窗口、优先级)。然而,尽管在解决这些VRP实例方面进行了数十年的扎实研究,但我们仍然看到优化的路线与实践者实际偏好的路线之间存在显着差距。这些差距大部分是由于被优化的内容和实践者实际关心的内容之间的差异,在许多情况下很难准确定义。在本文中,我们提出了一种新的分层路由优化与学习参数,结合了优化和机器学习方法的优势。我们的分层路由器首先解决了一个区域级的旅行商问题与学习的权重上的各种区域级别的功能,与区域访问序列固定,然后我们解决了停止级的车辆路径问题作为最短的哈密尔顿路径问题。贝叶斯优化方法,然后引入,使我们能够调整的权重分配给不同的区域功能用于解决区域级旅行推销员问题。通过使用Amazon Last Mile Routing Research Challenge提供的真实交付数据集,我们展示了同时拥有优化和机器学习组件的重要性。我们还演示了如何使用路由相关的功能来识别我们可能有困难的情况。这为进一步研究我们如何解决这些困难的情况铺平了道路。
New York University Tandon School of Engineering(纽约大学Tandon工程学院);University of California, San Diego(加州大学圣地亚哥分校);Stanford University(斯坦福大学);ServiceNow Research(ServiceNow研究);Mila - Quebec AI Institute(魁北克AI研究院);Université de Montréal(蒙特利尔大学)