Arch-Router：将LLM路由与人类偏好对齐
Arch-Router: Aligning LLM Routing with Human Preferences
AI总结：
提出Arch-Router，一个1.5B的偏好对齐路由框架，通过将查询映射到领域-动作偏好来匹配人类偏好，在对话数据集上达到SOTA，优于顶级专有模型，且支持无缝添加新模型。
摘要：
随着大型语言模型（LLM）的快速激增——每个模型针对不同的优势、风格或延迟/成本配置进行了优化——路由已成为操作化使用不同模型的关键技术。然而，现有的LLM路由方法在两个关键方面受到限制：它们使用基准来评估性能，而这些基准往往无法捕捉由主观评价标准驱动的人类偏好，并且它们通常从有限的模型池中进行选择。在这项工作中，我们提出了一种偏好对齐的路由框架，通过将查询匹配到用户定义的领域（例如，旅行）或动作类型（例如，图像编辑）来指导模型选择——提供了一种在路由决策中编码偏好的实用机制。具体来说，我们引入了\textbf{Arch-Router}，一个紧凑的1.5B模型，学习将查询映射到领域-动作偏好以进行模型路由决策。我们的方法还支持无缝添加新模型进行路由，而无需重新训练或架构修改。在对话数据集上的实验表明，我们的方法在将查询与人类偏好匹配方面达到了最先进（SOTA）的结果，优于顶级专有模型。我们的方法捕捉了主观评价标准，并使路由决策更加透明和灵活。我们的模型可在以下网址获取：\texttt{https://huggingface.co/katanemo/Arch-Router-1.5B}。
英文摘要：
With the rapid proliferation of large language models (LLMs) -- each optimized for different strengths, style, or latency/cost profile -- routing has become an essential technique to operationalize the use of different models. However, existing LLM routing approaches are limited in two key ways: they evaluate performance using benchmarks that often fail to capture human preferences driven by subjective evaluation criteria, and they typically select from a limited pool of models. In this work, we propose a preference-aligned routing framework that guides model selection by matching queries to user-defined domains (e.g., travel) or action types (e.g., image editing) -- offering a practical mechanism to encode preferences in routing decisions. Specifically, we introduce \textbf{Arch-Router}, a compact 1.5B model that learns to map queries to domain-action preferences for model routing decisions. Our approach also supports seamlessly adding new models for routing without requiring retraining or architectural modifications. Experiments on conversational datasets demonstrate that our approach achieves state-of-the-art (SOTA) results in matching queries with human preferences, outperforming top proprietary models. Our approach captures subjective evaluation criteria and makes routing decisions more transparent and flexible. Our model is available at: \texttt{https://huggingface.co/katanemo/Arch-Router-1.5B}.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
