设计机制防止大模型服务提供商欺骗用户，确保用户付第二优价格却获得最优体验。
Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers
- 基于博弈论设计激励相容机制，让用户能对抗服务商的欺诈行为。
- 理论证明机制可实现接近最优的用户效用，且误差随查询次数增长缓慢。
- 适用于对模型服务可信度敏感的开发者或企业用户，尤其关注成本效益。
通过API广泛使用的大型语言模型（LLMs）存在严重漏洞：服务提供商可能进行不诚实操作，例如暗中用低成本模型替换宣称的高性能模型，或在响应中插入无意义符号以增加计费。本文从算法博弈论和机制设计角度解决此问题，首次构建了真实用户-提供者生态系统的正式经济模型。用户可向多个模型提供商迭代提交$T$次查询，而提供商可采取多种策略行为。核心贡献为：对于连续策略空间及任意$ε∈(0,\frac{1}{2})$，存在一种近似激励相容机制，其加性近似比为$O(T^{1-ε}\log T)$，并保证用户的准线性第二优效用。同时证明了任何机制都无法在期望用户效用上显著优于该机制。模拟实验验证了机制在真实API设置下的有效性。
原文摘要 · Abstract (English)
The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: the potential for dishonest manipulation by service providers. This manipulation can manifest in various forms, such as secretly substituting a proclaimed high-performance model with a low-cost alternative, or inflating responses with meaningless tokens to increase billing. This work tackles the issue through the lens of algorithmic game theory and mechanism design. We are the first to propose a formal economic model for a realistic user-provider ecosystem, where a user can iteratively delegate $T$ queries to multiple model providers, and providers can engage in a range of strategic behaviors. As our central contribution, we prove that for a continuous strategy space and any $ε\in(0,\frac12)$, there exists an approximate incentive-compatible mechanism with an additive approximation ratio of $O(T^{1-ε}\log T)$, and a guaranteed quasi-linear second-best user utility. We also prove an impossibility result, stating that no mechanism can guarantee an expected user utility that is asymptotically better than our mechanism. Furthermore, we demonstrate the effectiveness of our mechanism in simulation experiments with real-world API settings.
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。