无需重新训练，新模型可零样本接入大语言模型路由系统。
Breaking Model Lock-in: Cost-Efficient Zero-Shot LLM Routing via a Universal Latent Space
- 构建通用隐空间，分离查询难度与模型特征
- 实现零样本接入，准确率更高且成本更低
- 适合需要快速集成新模型的系统开发者
大型语言模型（LLMs）的迅猛发展导致生态系统碎片化，形成“模型锁定”状态，无缝集成新模型仍是一大瓶颈。现有路由框架需耗时费力的全量重训，制约可扩展性与灵活性。本文提出零样本路由新范式ZeroRouter，基于一个模型无关的通用隐空间，该空间表征查询难度，从根本上解耦查询表征与模型评估。这使得新模型可零样本接入，无需大规模重训。ZeroRouter包含上下文感知预测器，将查询映射至该通用空间，以及双模式优化器，平衡准确率、成本与延迟。实验表明，本框架持续优于所有基线，在更低成本和延迟下实现更高准确率。
原文摘要 · Abstract (English)
The rapid proliferation of Large Language Models (LLMs) has led to a fragmented and inefficient ecosystem, a state of ``model lock-in'' where seamlessly integrating novel models remains a significant bottleneck. Current routing frameworks require exhaustive, costly retraining, hindering scalability and adaptability. We introduce ZeroRouter, a new paradigm for LLM routing that breaks this lock-in. Our approach is founded on a universal latent space, a model-agnostic representation of query difficulty that fundamentally decouples the characterization of a query from the profiling of a model. This allows for zero-shot onboarding of new models without full-scale retraining. ZeroRouter features a context-aware predictor that maps queries to this universal space and a dual-mode optimizer that balances accuracy, cost, and latency. Our framework consistently outperforms all baselines, delivering higher accuracy at lower cost and latency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。